1 |
DENIED
|
ROLE_USER
|
null |
|
Show voter details
|
2 |
DENIED
|
moderate
|
App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
} |
|
Show voter details
|
3 |
DENIED
|
edit
|
App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
} |
|
Show voter details
|
4 |
DENIED
|
moderate
|
App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
} |
|
Show voter details
|
5 |
DENIED
|
ROLE_USER
|
null |
|
Show voter details
|
6 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4055
+user: App\Entity\User {#4004 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "google execs: "great! now exploit the fuck out of it before they fix it so we can add that data to our own.""
+lang: "en"
+isAdult: false
+favouriteCount: 7
+score: 0
+lastActive: DateTime @1701279899 {#3965
date: 2023-11-29 18:44:59.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4053 …}
+nested: Doctrine\ORM\PersistentCollection {#4051 …}
+votes: Doctrine\ORM\PersistentCollection {#4049 …}
+reports: Doctrine\ORM\PersistentCollection {#4047 …}
+favourites: Doctrine\ORM\PersistentCollection {#4015 …}
+notifications: Doctrine\ORM\PersistentCollection {#4019 …}
-id: 177680
-bodyTs: "'add':18 'data':20 'exec':2 'exploit':5 'fix':13 'fuck':7 'googl':1 'great':3"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071/-/comment/3841632"
+editedAt: null
+createdAt: DateTimeImmutable @1701279899 {#4001
date: 2023-11-29 18:44:59.0 +01:00
}
} |
|
Show voter details
|
7 |
DENIED
|
edit
|
App\Entity\EntryComment {#4055
+user: App\Entity\User {#4004 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "google execs: "great! now exploit the fuck out of it before they fix it so we can add that data to our own.""
+lang: "en"
+isAdult: false
+favouriteCount: 7
+score: 0
+lastActive: DateTime @1701279899 {#3965
date: 2023-11-29 18:44:59.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4053 …}
+nested: Doctrine\ORM\PersistentCollection {#4051 …}
+votes: Doctrine\ORM\PersistentCollection {#4049 …}
+reports: Doctrine\ORM\PersistentCollection {#4047 …}
+favourites: Doctrine\ORM\PersistentCollection {#4015 …}
+notifications: Doctrine\ORM\PersistentCollection {#4019 …}
-id: 177680
-bodyTs: "'add':18 'data':20 'exec':2 'exploit':5 'fix':13 'fuck':7 'googl':1 'great':3"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071/-/comment/3841632"
+editedAt: null
+createdAt: DateTimeImmutable @1701279899 {#4001
date: 2023-11-29 18:44:59.0 +01:00
}
} |
|
Show voter details
|
8 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4055
+user: App\Entity\User {#4004 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "google execs: "great! now exploit the fuck out of it before they fix it so we can add that data to our own.""
+lang: "en"
+isAdult: false
+favouriteCount: 7
+score: 0
+lastActive: DateTime @1701279899 {#3965
date: 2023-11-29 18:44:59.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4053 …}
+nested: Doctrine\ORM\PersistentCollection {#4051 …}
+votes: Doctrine\ORM\PersistentCollection {#4049 …}
+reports: Doctrine\ORM\PersistentCollection {#4047 …}
+favourites: Doctrine\ORM\PersistentCollection {#4015 …}
+notifications: Doctrine\ORM\PersistentCollection {#4019 …}
-id: 177680
-bodyTs: "'add':18 'data':20 'exec':2 'exploit':5 'fix':13 'fuck':7 'googl':1 'great':3"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071/-/comment/3841632"
+editedAt: null
+createdAt: DateTimeImmutable @1701279899 {#4001
date: 2023-11-29 18:44:59.0 +01:00
}
} |
|
Show voter details
|
9 |
DENIED
|
ROLE_USER
|
null |
|
Show voter details
|
10 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
} |
|
Show voter details
|
11 |
DENIED
|
edit
|
App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
} |
|
Show voter details
|
12 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
} |
|
Show voter details
|
13 |
DENIED
|
ROLE_USER
|
null |
|
Show voter details
|
14 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4264
+user: Proxies\__CG__\App\Entity\User {#4267 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "Don’t doubt that they’re doing this for evil reasons"
+lang: "en"
+isAdult: false
+favouriteCount: 17
+score: 0
+lastActive: DateTime @1701290366 {#4263
date: 2023-11-29 21:39:26.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4271 …}
+nested: Doctrine\ORM\PersistentCollection {#4273 …}
+votes: Doctrine\ORM\PersistentCollection {#4269 …}
+reports: Doctrine\ORM\PersistentCollection {#4275 …}
+favourites: Doctrine\ORM\PersistentCollection {#4277 …}
+notifications: Doctrine\ORM\PersistentCollection {#4279 …}
-id: 178161
-bodyTs: "'doubt':3 'evil':10 're':6 'reason':11"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679143"
+editedAt: null
+createdAt: DateTimeImmutable @1701290366 {#4260
date: 2023-11-29 21:39:26.0 +01:00
}
} |
|
Show voter details
|
15 |
DENIED
|
edit
|
App\Entity\EntryComment {#4264
+user: Proxies\__CG__\App\Entity\User {#4267 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "Don’t doubt that they’re doing this for evil reasons"
+lang: "en"
+isAdult: false
+favouriteCount: 17
+score: 0
+lastActive: DateTime @1701290366 {#4263
date: 2023-11-29 21:39:26.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4271 …}
+nested: Doctrine\ORM\PersistentCollection {#4273 …}
+votes: Doctrine\ORM\PersistentCollection {#4269 …}
+reports: Doctrine\ORM\PersistentCollection {#4275 …}
+favourites: Doctrine\ORM\PersistentCollection {#4277 …}
+notifications: Doctrine\ORM\PersistentCollection {#4279 …}
-id: 178161
-bodyTs: "'doubt':3 'evil':10 're':6 'reason':11"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679143"
+editedAt: null
+createdAt: DateTimeImmutable @1701290366 {#4260
date: 2023-11-29 21:39:26.0 +01:00
}
} |
|
Show voter details
|
16 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4264
+user: Proxies\__CG__\App\Entity\User {#4267 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "Don’t doubt that they’re doing this for evil reasons"
+lang: "en"
+isAdult: false
+favouriteCount: 17
+score: 0
+lastActive: DateTime @1701290366 {#4263
date: 2023-11-29 21:39:26.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4271 …}
+nested: Doctrine\ORM\PersistentCollection {#4273 …}
+votes: Doctrine\ORM\PersistentCollection {#4269 …}
+reports: Doctrine\ORM\PersistentCollection {#4275 …}
+favourites: Doctrine\ORM\PersistentCollection {#4277 …}
+notifications: Doctrine\ORM\PersistentCollection {#4279 …}
-id: 178161
-bodyTs: "'doubt':3 'evil':10 're':6 'reason':11"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679143"
+editedAt: null
+createdAt: DateTimeImmutable @1701290366 {#4260
date: 2023-11-29 21:39:26.0 +01:00
}
} |
|
Show voter details
|
17 |
DENIED
|
ROLE_USER
|
null |
|
Show voter details
|
18 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4324
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4264
+user: Proxies\__CG__\App\Entity\User {#4267 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "Don’t doubt that they’re doing this for evil reasons"
+lang: "en"
+isAdult: false
+favouriteCount: 17
+score: 0
+lastActive: DateTime @1701290366 {#4263
date: 2023-11-29 21:39:26.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4271 …}
+nested: Doctrine\ORM\PersistentCollection {#4273 …}
+votes: Doctrine\ORM\PersistentCollection {#4269 …}
+reports: Doctrine\ORM\PersistentCollection {#4275 …}
+favourites: Doctrine\ORM\PersistentCollection {#4277 …}
+notifications: Doctrine\ORM\PersistentCollection {#4279 …}
-id: 178161
-bodyTs: "'doubt':3 'evil':10 're':6 'reason':11"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679143"
+editedAt: null
+createdAt: DateTimeImmutable @1701290366 {#4260
date: 2023-11-29 21:39:26.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "There’s an appealing notion to me that an evil upon an evil is closer to weighingout towards the good sometimes as a form of karmic retribution that can play out beneficially sometimez"
+lang: "en"
+isAdult: false
+favouriteCount: 3
+score: 0
+lastActive: DateTime @1701290610 {#4325
date: 2023-11-29 21:43:30.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
"@PotatoKat@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4321 …}
+nested: Doctrine\ORM\PersistentCollection {#4317 …}
+votes: Doctrine\ORM\PersistentCollection {#4315 …}
+reports: Doctrine\ORM\PersistentCollection {#4330 …}
+favourites: Doctrine\ORM\PersistentCollection {#4332 …}
+notifications: Doctrine\ORM\PersistentCollection {#4334 …}
-id: 178175
-bodyTs: "'appeal':4 'benefici':32 'closer':15 'evil':10,13 'form':24 'good':20 'karmic':26 'notion':5 'play':30 'retribut':27 'sometim':21 'sometimez':33 'toward':18 'upon':11 'weighingout':17"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679214"
+editedAt: null
+createdAt: DateTimeImmutable @1701290610 {#4328
date: 2023-11-29 21:43:30.0 +01:00
}
} |
|
Show voter details
|
19 |
DENIED
|
edit
|
App\Entity\EntryComment {#4324
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4264
+user: Proxies\__CG__\App\Entity\User {#4267 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "Don’t doubt that they’re doing this for evil reasons"
+lang: "en"
+isAdult: false
+favouriteCount: 17
+score: 0
+lastActive: DateTime @1701290366 {#4263
date: 2023-11-29 21:39:26.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4271 …}
+nested: Doctrine\ORM\PersistentCollection {#4273 …}
+votes: Doctrine\ORM\PersistentCollection {#4269 …}
+reports: Doctrine\ORM\PersistentCollection {#4275 …}
+favourites: Doctrine\ORM\PersistentCollection {#4277 …}
+notifications: Doctrine\ORM\PersistentCollection {#4279 …}
-id: 178161
-bodyTs: "'doubt':3 'evil':10 're':6 'reason':11"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679143"
+editedAt: null
+createdAt: DateTimeImmutable @1701290366 {#4260
date: 2023-11-29 21:39:26.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "There’s an appealing notion to me that an evil upon an evil is closer to weighingout towards the good sometimes as a form of karmic retribution that can play out beneficially sometimez"
+lang: "en"
+isAdult: false
+favouriteCount: 3
+score: 0
+lastActive: DateTime @1701290610 {#4325
date: 2023-11-29 21:43:30.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
"@PotatoKat@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4321 …}
+nested: Doctrine\ORM\PersistentCollection {#4317 …}
+votes: Doctrine\ORM\PersistentCollection {#4315 …}
+reports: Doctrine\ORM\PersistentCollection {#4330 …}
+favourites: Doctrine\ORM\PersistentCollection {#4332 …}
+notifications: Doctrine\ORM\PersistentCollection {#4334 …}
-id: 178175
-bodyTs: "'appeal':4 'benefici':32 'closer':15 'evil':10,13 'form':24 'good':20 'karmic':26 'notion':5 'play':30 'retribut':27 'sometim':21 'sometimez':33 'toward':18 'upon':11 'weighingout':17"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679214"
+editedAt: null
+createdAt: DateTimeImmutable @1701290610 {#4328
date: 2023-11-29 21:43:30.0 +01:00
}
} |
|
Show voter details
|
20 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4324
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4264
+user: Proxies\__CG__\App\Entity\User {#4267 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "Don’t doubt that they’re doing this for evil reasons"
+lang: "en"
+isAdult: false
+favouriteCount: 17
+score: 0
+lastActive: DateTime @1701290366 {#4263
date: 2023-11-29 21:39:26.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4271 …}
+nested: Doctrine\ORM\PersistentCollection {#4273 …}
+votes: Doctrine\ORM\PersistentCollection {#4269 …}
+reports: Doctrine\ORM\PersistentCollection {#4275 …}
+favourites: Doctrine\ORM\PersistentCollection {#4277 …}
+notifications: Doctrine\ORM\PersistentCollection {#4279 …}
-id: 178161
-bodyTs: "'doubt':3 'evil':10 're':6 'reason':11"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679143"
+editedAt: null
+createdAt: DateTimeImmutable @1701290366 {#4260
date: 2023-11-29 21:39:26.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "There’s an appealing notion to me that an evil upon an evil is closer to weighingout towards the good sometimes as a form of karmic retribution that can play out beneficially sometimez"
+lang: "en"
+isAdult: false
+favouriteCount: 3
+score: 0
+lastActive: DateTime @1701290610 {#4325
date: 2023-11-29 21:43:30.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
"@PotatoKat@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4321 …}
+nested: Doctrine\ORM\PersistentCollection {#4317 …}
+votes: Doctrine\ORM\PersistentCollection {#4315 …}
+reports: Doctrine\ORM\PersistentCollection {#4330 …}
+favourites: Doctrine\ORM\PersistentCollection {#4332 …}
+notifications: Doctrine\ORM\PersistentCollection {#4334 …}
-id: 178175
-bodyTs: "'appeal':4 'benefici':32 'closer':15 'evil':10,13 'form':24 'good':20 'karmic':26 'notion':5 'play':30 'retribut':27 'sometim':21 'sometimez':33 'toward':18 'upon':11 'weighingout':17"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679214"
+editedAt: null
+createdAt: DateTimeImmutable @1701290610 {#4328
date: 2023-11-29 21:43:30.0 +01:00
}
} |
|
Show voter details
|
21 |
DENIED
|
ROLE_USER
|
null |
|
Show voter details
|
22 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4283
+user: Proxies\__CG__\App\Entity\User {#4284 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "google is probably trying to take out competing ai"
+lang: "en"
+isAdult: false
+favouriteCount: 14
+score: 0
+lastActive: DateTime @1701294372 {#4281
date: 2023-11-29 22:46:12.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4285 …}
+nested: Doctrine\ORM\PersistentCollection {#4287 …}
+votes: Doctrine\ORM\PersistentCollection {#4289 …}
+reports: Doctrine\ORM\PersistentCollection {#4291 …}
+favourites: Doctrine\ORM\PersistentCollection {#4293 …}
+notifications: Doctrine\ORM\PersistentCollection {#4295 …}
-id: 178462
-bodyTs: "'ai':9 'compet':8 'googl':1 'probabl':3 'take':6 'tri':4"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://sopuli.xyz/comment/5007445"
+editedAt: null
+createdAt: DateTimeImmutable @1701294372 {#4282
date: 2023-11-29 22:46:12.0 +01:00
}
} |
|
Show voter details
|
23 |
DENIED
|
edit
|
App\Entity\EntryComment {#4283
+user: Proxies\__CG__\App\Entity\User {#4284 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "google is probably trying to take out competing ai"
+lang: "en"
+isAdult: false
+favouriteCount: 14
+score: 0
+lastActive: DateTime @1701294372 {#4281
date: 2023-11-29 22:46:12.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4285 …}
+nested: Doctrine\ORM\PersistentCollection {#4287 …}
+votes: Doctrine\ORM\PersistentCollection {#4289 …}
+reports: Doctrine\ORM\PersistentCollection {#4291 …}
+favourites: Doctrine\ORM\PersistentCollection {#4293 …}
+notifications: Doctrine\ORM\PersistentCollection {#4295 …}
-id: 178462
-bodyTs: "'ai':9 'compet':8 'googl':1 'probabl':3 'take':6 'tri':4"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://sopuli.xyz/comment/5007445"
+editedAt: null
+createdAt: DateTimeImmutable @1701294372 {#4282
date: 2023-11-29 22:46:12.0 +01:00
}
} |
|
Show voter details
|
24 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4283
+user: Proxies\__CG__\App\Entity\User {#4284 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "google is probably trying to take out competing ai"
+lang: "en"
+isAdult: false
+favouriteCount: 14
+score: 0
+lastActive: DateTime @1701294372 {#4281
date: 2023-11-29 22:46:12.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4285 …}
+nested: Doctrine\ORM\PersistentCollection {#4287 …}
+votes: Doctrine\ORM\PersistentCollection {#4289 …}
+reports: Doctrine\ORM\PersistentCollection {#4291 …}
+favourites: Doctrine\ORM\PersistentCollection {#4293 …}
+notifications: Doctrine\ORM\PersistentCollection {#4295 …}
-id: 178462
-bodyTs: "'ai':9 'compet':8 'googl':1 'probabl':3 'take':6 'tri':4"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://sopuli.xyz/comment/5007445"
+editedAt: null
+createdAt: DateTimeImmutable @1701294372 {#4282
date: 2023-11-29 22:46:12.0 +01:00
}
} |
|
Show voter details
|
25 |
DENIED
|
ROLE_USER
|
null |
|
Show voter details
|
26 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4338
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4283
+user: Proxies\__CG__\App\Entity\User {#4284 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "google is probably trying to take out competing ai"
+lang: "en"
+isAdult: false
+favouriteCount: 14
+score: 0
+lastActive: DateTime @1701294372 {#4281
date: 2023-11-29 22:46:12.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4285 …}
+nested: Doctrine\ORM\PersistentCollection {#4287 …}
+votes: Doctrine\ORM\PersistentCollection {#4289 …}
+reports: Doctrine\ORM\PersistentCollection {#4291 …}
+favourites: Doctrine\ORM\PersistentCollection {#4293 …}
+notifications: Doctrine\ORM\PersistentCollection {#4295 …}
-id: 178462
-bodyTs: "'ai':9 'compet':8 'googl':1 'probabl':3 'take':6 'tri':4"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://sopuli.xyz/comment/5007445"
+editedAt: null
+createdAt: DateTimeImmutable @1701294372 {#4282
date: 2023-11-29 22:46:12.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "I’m glad we live in a time where something so groundbreaking and revolutionary is set to become freely accessible to all. Just gotta regulate the regulators so everyone gets a fair shake when all is said and done"
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1701295625 {#4336
date: 2023-11-29 23:07:05.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
"@reksas@sopuli.xyz"
]
+children: Doctrine\ORM\PersistentCollection {#4339 …}
+nested: Doctrine\ORM\PersistentCollection {#4341 …}
+votes: Doctrine\ORM\PersistentCollection {#4343 …}
+reports: Doctrine\ORM\PersistentCollection {#4345 …}
+favourites: Doctrine\ORM\PersistentCollection {#4347 …}
+notifications: Doctrine\ORM\PersistentCollection {#4349 …}
-id: 178554
-bodyTs: "'access':20 'becom':18 'done':39 'everyon':29 'fair':32 'freeli':19 'get':30 'glad':3 'gotta':24 'groundbreak':12 'live':5 'm':2 'regul':25,27 'revolutionari':14 'said':37 'set':16 'shake':33 'someth':10 'time':8"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5681038"
+editedAt: null
+createdAt: DateTimeImmutable @1701295625 {#4337
date: 2023-11-29 23:07:05.0 +01:00
}
} |
|
Show voter details
|
27 |
DENIED
|
edit
|
App\Entity\EntryComment {#4338
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4283
+user: Proxies\__CG__\App\Entity\User {#4284 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "google is probably trying to take out competing ai"
+lang: "en"
+isAdult: false
+favouriteCount: 14
+score: 0
+lastActive: DateTime @1701294372 {#4281
date: 2023-11-29 22:46:12.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4285 …}
+nested: Doctrine\ORM\PersistentCollection {#4287 …}
+votes: Doctrine\ORM\PersistentCollection {#4289 …}
+reports: Doctrine\ORM\PersistentCollection {#4291 …}
+favourites: Doctrine\ORM\PersistentCollection {#4293 …}
+notifications: Doctrine\ORM\PersistentCollection {#4295 …}
-id: 178462
-bodyTs: "'ai':9 'compet':8 'googl':1 'probabl':3 'take':6 'tri':4"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://sopuli.xyz/comment/5007445"
+editedAt: null
+createdAt: DateTimeImmutable @1701294372 {#4282
date: 2023-11-29 22:46:12.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "I’m glad we live in a time where something so groundbreaking and revolutionary is set to become freely accessible to all. Just gotta regulate the regulators so everyone gets a fair shake when all is said and done"
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1701295625 {#4336
date: 2023-11-29 23:07:05.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
"@reksas@sopuli.xyz"
]
+children: Doctrine\ORM\PersistentCollection {#4339 …}
+nested: Doctrine\ORM\PersistentCollection {#4341 …}
+votes: Doctrine\ORM\PersistentCollection {#4343 …}
+reports: Doctrine\ORM\PersistentCollection {#4345 …}
+favourites: Doctrine\ORM\PersistentCollection {#4347 …}
+notifications: Doctrine\ORM\PersistentCollection {#4349 …}
-id: 178554
-bodyTs: "'access':20 'becom':18 'done':39 'everyon':29 'fair':32 'freeli':19 'get':30 'glad':3 'gotta':24 'groundbreak':12 'live':5 'm':2 'regul':25,27 'revolutionari':14 'said':37 'set':16 'shake':33 'someth':10 'time':8"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5681038"
+editedAt: null
+createdAt: DateTimeImmutable @1701295625 {#4337
date: 2023-11-29 23:07:05.0 +01:00
}
} |
|
Show voter details
|
28 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4338
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4283
+user: Proxies\__CG__\App\Entity\User {#4284 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4100
+user: App\Entity\User {#4084 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: "Finally Google not being evil"
+lang: "en"
+isAdult: false
+favouriteCount: 5
+score: 0
+lastActive: DateTime @1702226335 {#4106
date: 2023-12-10 17:38:55.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4092 …}
+nested: Doctrine\ORM\PersistentCollection {#4095 …}
+votes: Doctrine\ORM\PersistentCollection {#4093 …}
+reports: Doctrine\ORM\PersistentCollection {#4091 …}
+favourites: Doctrine\ORM\PersistentCollection {#4090 …}
+notifications: Doctrine\ORM\PersistentCollection {#4081 …}
-id: 178145
-bodyTs: "'evil':5 'final':1 'googl':2"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5679051"
+editedAt: null
+createdAt: DateTimeImmutable @1701290149 {#4104
date: 2023-11-29 21:35:49.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "google is probably trying to take out competing ai"
+lang: "en"
+isAdult: false
+favouriteCount: 14
+score: 0
+lastActive: DateTime @1701294372 {#4281
date: 2023-11-29 22:46:12.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
]
+children: Doctrine\ORM\PersistentCollection {#4285 …}
+nested: Doctrine\ORM\PersistentCollection {#4287 …}
+votes: Doctrine\ORM\PersistentCollection {#4289 …}
+reports: Doctrine\ORM\PersistentCollection {#4291 …}
+favourites: Doctrine\ORM\PersistentCollection {#4293 …}
+notifications: Doctrine\ORM\PersistentCollection {#4295 …}
-id: 178462
-bodyTs: "'ai':9 'compet':8 'googl':1 'probabl':3 'take':6 'tri':4"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://sopuli.xyz/comment/5007445"
+editedAt: null
+createdAt: DateTimeImmutable @1701294372 {#4282
date: 2023-11-29 22:46:12.0 +01:00
}
}
+root: App\Entity\EntryComment {#4100}
+body: "I’m glad we live in a time where something so groundbreaking and revolutionary is set to become freely accessible to all. Just gotta regulate the regulators so everyone gets a fair shake when all is said and done"
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1701295625 {#4336
date: 2023-11-29 23:07:05.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@cheese_greater@lemmy.world"
"@reksas@sopuli.xyz"
]
+children: Doctrine\ORM\PersistentCollection {#4339 …}
+nested: Doctrine\ORM\PersistentCollection {#4341 …}
+votes: Doctrine\ORM\PersistentCollection {#4343 …}
+reports: Doctrine\ORM\PersistentCollection {#4345 …}
+favourites: Doctrine\ORM\PersistentCollection {#4347 …}
+notifications: Doctrine\ORM\PersistentCollection {#4349 …}
-id: 178554
-bodyTs: "'access':20 'becom':18 'done':39 'everyon':29 'fair':32 'freeli':19 'get':30 'glad':3 'gotta':24 'groundbreak':12 'live':5 'm':2 'regul':25,27 'revolutionari':14 'said':37 'set':16 'shake':33 'someth':10 'time':8"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.world/comment/5681038"
+editedAt: null
+createdAt: DateTimeImmutable @1701295625 {#4337
date: 2023-11-29 23:07:05.0 +01:00
}
} |
|
Show voter details
|
29 |
DENIED
|
ROLE_USER
|
null |
|
Show voter details
|
30 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4168
+user: App\Entity\User {#4181 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: """
AI really did that thing where you repeat a word so often that it loses meaning and the rest of the world eventually starts to turn to mush.\n
\n
Jokes aside, I think I know why it does this: Because by giving it a STUPIDLY easy prompt it can rack up huge amounts of reward function, once you accumulate enough it no longer becomes bound by it and it will simply act in whatever the easiest action to continue gaining points is: in this case, it’s reading its training data rather than doing the usual “machine learning” obfuscating that it normally does. Maybe this is a result of repeating a word over and over giving an exponentially rising score until it eventually hits +INF, effectively disabling it? Seems a little contrived but it’s an avenue worth investigating.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1702486394 {#4162
date: 2023-12-13 17:53:14.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4169 …}
+nested: Doctrine\ORM\PersistentCollection {#4171 …}
+votes: Doctrine\ORM\PersistentCollection {#4173 …}
+reports: Doctrine\ORM\PersistentCollection {#4175 …}
+favourites: Doctrine\ORM\PersistentCollection {#4177 …}
+notifications: Doctrine\ORM\PersistentCollection {#4179 …}
-id: 183826
-bodyTs: "'accumul':58 'act':71 'action':76 'ai':1 'amount':52 'asid':30 'avenu':136 'becom':63 'bound':64 'case':84 'continu':78 'contriv':131 'data':90 'disabl':126 'easi':45 'easiest':75 'effect':125 'enough':59 'eventu':23,122 'exponenti':117 'function':55 'gain':79 'give':41,115 'hit':123 'huge':51 'inf':124 'investig':138 'joke':29 'know':34 'learn':97 'littl':130 'longer':62 'lose':15 'machin':96 'mayb':103 'mean':16 'mush':28 'normal':101 'obfusc':98 'often':12 'point':80 'prompt':46 'rack':49 'rather':91 'read':87 'realli':2 'repeat':8,109 'rest':19 'result':107 'reward':54 'rise':118 'score':119 'seem':128 'simpli':70 'start':24 'stupid':44 'thing':5 'think':32 'train':89 'turn':26 'usual':95 'whatev':73 'word':10,111 'world':22 'worth':137"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.ml/comment/6257022"
+editedAt: DateTimeImmutable @1702480541 {#4163
date: 2023-12-13 16:15:41.0 +01:00
}
+createdAt: DateTimeImmutable @1701359642 {#4164
date: 2023-11-30 16:54:02.0 +01:00
}
} |
|
Show voter details
|
31 |
DENIED
|
edit
|
App\Entity\EntryComment {#4168
+user: App\Entity\User {#4181 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: """
AI really did that thing where you repeat a word so often that it loses meaning and the rest of the world eventually starts to turn to mush.\n
\n
Jokes aside, I think I know why it does this: Because by giving it a STUPIDLY easy prompt it can rack up huge amounts of reward function, once you accumulate enough it no longer becomes bound by it and it will simply act in whatever the easiest action to continue gaining points is: in this case, it’s reading its training data rather than doing the usual “machine learning” obfuscating that it normally does. Maybe this is a result of repeating a word over and over giving an exponentially rising score until it eventually hits +INF, effectively disabling it? Seems a little contrived but it’s an avenue worth investigating.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1702486394 {#4162
date: 2023-12-13 17:53:14.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4169 …}
+nested: Doctrine\ORM\PersistentCollection {#4171 …}
+votes: Doctrine\ORM\PersistentCollection {#4173 …}
+reports: Doctrine\ORM\PersistentCollection {#4175 …}
+favourites: Doctrine\ORM\PersistentCollection {#4177 …}
+notifications: Doctrine\ORM\PersistentCollection {#4179 …}
-id: 183826
-bodyTs: "'accumul':58 'act':71 'action':76 'ai':1 'amount':52 'asid':30 'avenu':136 'becom':63 'bound':64 'case':84 'continu':78 'contriv':131 'data':90 'disabl':126 'easi':45 'easiest':75 'effect':125 'enough':59 'eventu':23,122 'exponenti':117 'function':55 'gain':79 'give':41,115 'hit':123 'huge':51 'inf':124 'investig':138 'joke':29 'know':34 'learn':97 'littl':130 'longer':62 'lose':15 'machin':96 'mayb':103 'mean':16 'mush':28 'normal':101 'obfusc':98 'often':12 'point':80 'prompt':46 'rack':49 'rather':91 'read':87 'realli':2 'repeat':8,109 'rest':19 'result':107 'reward':54 'rise':118 'score':119 'seem':128 'simpli':70 'start':24 'stupid':44 'thing':5 'think':32 'train':89 'turn':26 'usual':95 'whatev':73 'word':10,111 'world':22 'worth':137"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.ml/comment/6257022"
+editedAt: DateTimeImmutable @1702480541 {#4163
date: 2023-12-13 16:15:41.0 +01:00
}
+createdAt: DateTimeImmutable @1701359642 {#4164
date: 2023-11-30 16:54:02.0 +01:00
}
} |
|
Show voter details
|
32 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4168
+user: App\Entity\User {#4181 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: """
AI really did that thing where you repeat a word so often that it loses meaning and the rest of the world eventually starts to turn to mush.\n
\n
Jokes aside, I think I know why it does this: Because by giving it a STUPIDLY easy prompt it can rack up huge amounts of reward function, once you accumulate enough it no longer becomes bound by it and it will simply act in whatever the easiest action to continue gaining points is: in this case, it’s reading its training data rather than doing the usual “machine learning” obfuscating that it normally does. Maybe this is a result of repeating a word over and over giving an exponentially rising score until it eventually hits +INF, effectively disabling it? Seems a little contrived but it’s an avenue worth investigating.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1702486394 {#4162
date: 2023-12-13 17:53:14.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4169 …}
+nested: Doctrine\ORM\PersistentCollection {#4171 …}
+votes: Doctrine\ORM\PersistentCollection {#4173 …}
+reports: Doctrine\ORM\PersistentCollection {#4175 …}
+favourites: Doctrine\ORM\PersistentCollection {#4177 …}
+notifications: Doctrine\ORM\PersistentCollection {#4179 …}
-id: 183826
-bodyTs: "'accumul':58 'act':71 'action':76 'ai':1 'amount':52 'asid':30 'avenu':136 'becom':63 'bound':64 'case':84 'continu':78 'contriv':131 'data':90 'disabl':126 'easi':45 'easiest':75 'effect':125 'enough':59 'eventu':23,122 'exponenti':117 'function':55 'gain':79 'give':41,115 'hit':123 'huge':51 'inf':124 'investig':138 'joke':29 'know':34 'learn':97 'littl':130 'longer':62 'lose':15 'machin':96 'mayb':103 'mean':16 'mush':28 'normal':101 'obfusc':98 'often':12 'point':80 'prompt':46 'rack':49 'rather':91 'read':87 'realli':2 'repeat':8,109 'rest':19 'result':107 'reward':54 'rise':118 'score':119 'seem':128 'simpli':70 'start':24 'stupid':44 'thing':5 'think':32 'train':89 'turn':26 'usual':95 'whatev':73 'word':10,111 'world':22 'worth':137"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.ml/comment/6257022"
+editedAt: DateTimeImmutable @1702480541 {#4163
date: 2023-12-13 16:15:41.0 +01:00
}
+createdAt: DateTimeImmutable @1701359642 {#4164
date: 2023-11-30 16:54:02.0 +01:00
}
} |
|
Show voter details
|
33 |
DENIED
|
ROLE_USER
|
null |
|
Show voter details
|
34 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4300
+user: Proxies\__CG__\App\Entity\User {#4301 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4168
+user: App\Entity\User {#4181 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: """
AI really did that thing where you repeat a word so often that it loses meaning and the rest of the world eventually starts to turn to mush.\n
\n
Jokes aside, I think I know why it does this: Because by giving it a STUPIDLY easy prompt it can rack up huge amounts of reward function, once you accumulate enough it no longer becomes bound by it and it will simply act in whatever the easiest action to continue gaining points is: in this case, it’s reading its training data rather than doing the usual “machine learning” obfuscating that it normally does. Maybe this is a result of repeating a word over and over giving an exponentially rising score until it eventually hits +INF, effectively disabling it? Seems a little contrived but it’s an avenue worth investigating.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1702486394 {#4162
date: 2023-12-13 17:53:14.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4169 …}
+nested: Doctrine\ORM\PersistentCollection {#4171 …}
+votes: Doctrine\ORM\PersistentCollection {#4173 …}
+reports: Doctrine\ORM\PersistentCollection {#4175 …}
+favourites: Doctrine\ORM\PersistentCollection {#4177 …}
+notifications: Doctrine\ORM\PersistentCollection {#4179 …}
-id: 183826
-bodyTs: "'accumul':58 'act':71 'action':76 'ai':1 'amount':52 'asid':30 'avenu':136 'becom':63 'bound':64 'case':84 'continu':78 'contriv':131 'data':90 'disabl':126 'easi':45 'easiest':75 'effect':125 'enough':59 'eventu':23,122 'exponenti':117 'function':55 'gain':79 'give':41,115 'hit':123 'huge':51 'inf':124 'investig':138 'joke':29 'know':34 'learn':97 'littl':130 'longer':62 'lose':15 'machin':96 'mayb':103 'mean':16 'mush':28 'normal':101 'obfusc':98 'often':12 'point':80 'prompt':46 'rack':49 'rather':91 'read':87 'realli':2 'repeat':8,109 'rest':19 'result':107 'reward':54 'rise':118 'score':119 'seem':128 'simpli':70 'start':24 'stupid':44 'thing':5 'think':32 'train':89 'turn':26 'usual':95 'whatev':73 'word':10,111 'world':22 'worth':137"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.ml/comment/6257022"
+editedAt: DateTimeImmutable @1702480541 {#4163
date: 2023-12-13 16:15:41.0 +01:00
}
+createdAt: DateTimeImmutable @1701359642 {#4164
date: 2023-11-30 16:54:02.0 +01:00
}
}
+root: App\Entity\EntryComment {#4168}
+body: """
I watched a video from a guy who used machine learning to play Pokemon and he did a great analysis of the process. The most interesting part to me was how small changes to the reward system could produce such bizarre and unexpected behavior. He gave out rewards for exploring new areas by taking screenshots after every input and then comparing them against every previous one. Suddenly it became very fixated on a specific area of the game and he couldn’t figure out why. Turns out there was both flowers and water animating in that area so it triggered a lot of rewards without actually exploring. The AI literally got distracted looking at the beautiful landscape!\n
\n
Anyway, that example helped me understand the challenges of this sort of software design. Super fascinating stuff.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 4
+score: 0
+lastActive: DateTime @1701388535 {#4297
date: 2023-12-01 00:55:35.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@Omega_Haxors@lemmy.ml"
]
+children: Doctrine\ORM\PersistentCollection {#4302 …}
+nested: Doctrine\ORM\PersistentCollection {#4304 …}
+votes: Doctrine\ORM\PersistentCollection {#4306 …}
+reports: Doctrine\ORM\PersistentCollection {#4308 …}
+favourites: Doctrine\ORM\PersistentCollection {#4310 …}
+notifications: Doctrine\ORM\PersistentCollection {#4312 …}
-id: 184172
-bodyTs: "'actual':106 'ai':109 'analysi':20 'anim':94 'anyway':118 'area':52,75,97 'beauti':116 'becam':69 'behavior':44 'bizarr':41 'challeng':125 'chang':33 'compar':61 'could':38 'couldn':81 'design':131 'distract':112 'everi':57,64 'exampl':120 'explor':50,107 'fascin':133 'figur':83 'fixat':71 'flower':91 'game':78 'gave':46 'got':111 'great':19 'guy':7 'help':121 'input':58 'interest':26 'landscap':117 'learn':11 'liter':110 'look':113 'lot':102 'machin':10 'new':51 'one':66 'part':27 'play':13 'pokemon':14 'previous':65 'process':23 'produc':39 'reward':36,48,104 'screenshot':55 'small':32 'softwar':130 'sort':128 'specif':74 'stuff':134 'sudden':67 'super':132 'system':37 'take':54 'trigger':100 'turn':86 'understand':123 'unexpect':43 'use':9 'video':4 'watch':2 'water':93 'without':105"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://corndog.social/comment/1430879"
+editedAt: DateTimeImmutable @1702486405 {#4298
date: 2023-12-13 17:53:25.0 +01:00
}
+createdAt: DateTimeImmutable @1701388535 {#4299
date: 2023-12-01 00:55:35.0 +01:00
}
} |
|
Show voter details
|
35 |
DENIED
|
edit
|
App\Entity\EntryComment {#4300
+user: Proxies\__CG__\App\Entity\User {#4301 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4168
+user: App\Entity\User {#4181 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: """
AI really did that thing where you repeat a word so often that it loses meaning and the rest of the world eventually starts to turn to mush.\n
\n
Jokes aside, I think I know why it does this: Because by giving it a STUPIDLY easy prompt it can rack up huge amounts of reward function, once you accumulate enough it no longer becomes bound by it and it will simply act in whatever the easiest action to continue gaining points is: in this case, it’s reading its training data rather than doing the usual “machine learning” obfuscating that it normally does. Maybe this is a result of repeating a word over and over giving an exponentially rising score until it eventually hits +INF, effectively disabling it? Seems a little contrived but it’s an avenue worth investigating.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1702486394 {#4162
date: 2023-12-13 17:53:14.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4169 …}
+nested: Doctrine\ORM\PersistentCollection {#4171 …}
+votes: Doctrine\ORM\PersistentCollection {#4173 …}
+reports: Doctrine\ORM\PersistentCollection {#4175 …}
+favourites: Doctrine\ORM\PersistentCollection {#4177 …}
+notifications: Doctrine\ORM\PersistentCollection {#4179 …}
-id: 183826
-bodyTs: "'accumul':58 'act':71 'action':76 'ai':1 'amount':52 'asid':30 'avenu':136 'becom':63 'bound':64 'case':84 'continu':78 'contriv':131 'data':90 'disabl':126 'easi':45 'easiest':75 'effect':125 'enough':59 'eventu':23,122 'exponenti':117 'function':55 'gain':79 'give':41,115 'hit':123 'huge':51 'inf':124 'investig':138 'joke':29 'know':34 'learn':97 'littl':130 'longer':62 'lose':15 'machin':96 'mayb':103 'mean':16 'mush':28 'normal':101 'obfusc':98 'often':12 'point':80 'prompt':46 'rack':49 'rather':91 'read':87 'realli':2 'repeat':8,109 'rest':19 'result':107 'reward':54 'rise':118 'score':119 'seem':128 'simpli':70 'start':24 'stupid':44 'thing':5 'think':32 'train':89 'turn':26 'usual':95 'whatev':73 'word':10,111 'world':22 'worth':137"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.ml/comment/6257022"
+editedAt: DateTimeImmutable @1702480541 {#4163
date: 2023-12-13 16:15:41.0 +01:00
}
+createdAt: DateTimeImmutable @1701359642 {#4164
date: 2023-11-30 16:54:02.0 +01:00
}
}
+root: App\Entity\EntryComment {#4168}
+body: """
I watched a video from a guy who used machine learning to play Pokemon and he did a great analysis of the process. The most interesting part to me was how small changes to the reward system could produce such bizarre and unexpected behavior. He gave out rewards for exploring new areas by taking screenshots after every input and then comparing them against every previous one. Suddenly it became very fixated on a specific area of the game and he couldn’t figure out why. Turns out there was both flowers and water animating in that area so it triggered a lot of rewards without actually exploring. The AI literally got distracted looking at the beautiful landscape!\n
\n
Anyway, that example helped me understand the challenges of this sort of software design. Super fascinating stuff.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 4
+score: 0
+lastActive: DateTime @1701388535 {#4297
date: 2023-12-01 00:55:35.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@Omega_Haxors@lemmy.ml"
]
+children: Doctrine\ORM\PersistentCollection {#4302 …}
+nested: Doctrine\ORM\PersistentCollection {#4304 …}
+votes: Doctrine\ORM\PersistentCollection {#4306 …}
+reports: Doctrine\ORM\PersistentCollection {#4308 …}
+favourites: Doctrine\ORM\PersistentCollection {#4310 …}
+notifications: Doctrine\ORM\PersistentCollection {#4312 …}
-id: 184172
-bodyTs: "'actual':106 'ai':109 'analysi':20 'anim':94 'anyway':118 'area':52,75,97 'beauti':116 'becam':69 'behavior':44 'bizarr':41 'challeng':125 'chang':33 'compar':61 'could':38 'couldn':81 'design':131 'distract':112 'everi':57,64 'exampl':120 'explor':50,107 'fascin':133 'figur':83 'fixat':71 'flower':91 'game':78 'gave':46 'got':111 'great':19 'guy':7 'help':121 'input':58 'interest':26 'landscap':117 'learn':11 'liter':110 'look':113 'lot':102 'machin':10 'new':51 'one':66 'part':27 'play':13 'pokemon':14 'previous':65 'process':23 'produc':39 'reward':36,48,104 'screenshot':55 'small':32 'softwar':130 'sort':128 'specif':74 'stuff':134 'sudden':67 'super':132 'system':37 'take':54 'trigger':100 'turn':86 'understand':123 'unexpect':43 'use':9 'video':4 'watch':2 'water':93 'without':105"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://corndog.social/comment/1430879"
+editedAt: DateTimeImmutable @1702486405 {#4298
date: 2023-12-13 17:53:25.0 +01:00
}
+createdAt: DateTimeImmutable @1701388535 {#4299
date: 2023-12-01 00:55:35.0 +01:00
}
} |
|
Show voter details
|
36 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4300
+user: Proxies\__CG__\App\Entity\User {#4301 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: App\Entity\EntryComment {#4168
+user: App\Entity\User {#4181 …}
+entry: App\Entity\Entry {#2413}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: """
AI really did that thing where you repeat a word so often that it loses meaning and the rest of the world eventually starts to turn to mush.\n
\n
Jokes aside, I think I know why it does this: Because by giving it a STUPIDLY easy prompt it can rack up huge amounts of reward function, once you accumulate enough it no longer becomes bound by it and it will simply act in whatever the easiest action to continue gaining points is: in this case, it’s reading its training data rather than doing the usual “machine learning” obfuscating that it normally does. Maybe this is a result of repeating a word over and over giving an exponentially rising score until it eventually hits +INF, effectively disabling it? Seems a little contrived but it’s an avenue worth investigating.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1702486394 {#4162
date: 2023-12-13 17:53:14.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4169 …}
+nested: Doctrine\ORM\PersistentCollection {#4171 …}
+votes: Doctrine\ORM\PersistentCollection {#4173 …}
+reports: Doctrine\ORM\PersistentCollection {#4175 …}
+favourites: Doctrine\ORM\PersistentCollection {#4177 …}
+notifications: Doctrine\ORM\PersistentCollection {#4179 …}
-id: 183826
-bodyTs: "'accumul':58 'act':71 'action':76 'ai':1 'amount':52 'asid':30 'avenu':136 'becom':63 'bound':64 'case':84 'continu':78 'contriv':131 'data':90 'disabl':126 'easi':45 'easiest':75 'effect':125 'enough':59 'eventu':23,122 'exponenti':117 'function':55 'gain':79 'give':41,115 'hit':123 'huge':51 'inf':124 'investig':138 'joke':29 'know':34 'learn':97 'littl':130 'longer':62 'lose':15 'machin':96 'mayb':103 'mean':16 'mush':28 'normal':101 'obfusc':98 'often':12 'point':80 'prompt':46 'rack':49 'rather':91 'read':87 'realli':2 'repeat':8,109 'rest':19 'result':107 'reward':54 'rise':118 'score':119 'seem':128 'simpli':70 'start':24 'stupid':44 'thing':5 'think':32 'train':89 'turn':26 'usual':95 'whatev':73 'word':10,111 'world':22 'worth':137"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.ml/comment/6257022"
+editedAt: DateTimeImmutable @1702480541 {#4163
date: 2023-12-13 16:15:41.0 +01:00
}
+createdAt: DateTimeImmutable @1701359642 {#4164
date: 2023-11-30 16:54:02.0 +01:00
}
}
+root: App\Entity\EntryComment {#4168}
+body: """
I watched a video from a guy who used machine learning to play Pokemon and he did a great analysis of the process. The most interesting part to me was how small changes to the reward system could produce such bizarre and unexpected behavior. He gave out rewards for exploring new areas by taking screenshots after every input and then comparing them against every previous one. Suddenly it became very fixated on a specific area of the game and he couldn’t figure out why. Turns out there was both flowers and water animating in that area so it triggered a lot of rewards without actually exploring. The AI literally got distracted looking at the beautiful landscape!\n
\n
Anyway, that example helped me understand the challenges of this sort of software design. Super fascinating stuff.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 4
+score: 0
+lastActive: DateTime @1701388535 {#4297
date: 2023-12-01 00:55:35.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
"@Omega_Haxors@lemmy.ml"
]
+children: Doctrine\ORM\PersistentCollection {#4302 …}
+nested: Doctrine\ORM\PersistentCollection {#4304 …}
+votes: Doctrine\ORM\PersistentCollection {#4306 …}
+reports: Doctrine\ORM\PersistentCollection {#4308 …}
+favourites: Doctrine\ORM\PersistentCollection {#4310 …}
+notifications: Doctrine\ORM\PersistentCollection {#4312 …}
-id: 184172
-bodyTs: "'actual':106 'ai':109 'analysi':20 'anim':94 'anyway':118 'area':52,75,97 'beauti':116 'becam':69 'behavior':44 'bizarr':41 'challeng':125 'chang':33 'compar':61 'could':38 'couldn':81 'design':131 'distract':112 'everi':57,64 'exampl':120 'explor':50,107 'fascin':133 'figur':83 'fixat':71 'flower':91 'game':78 'gave':46 'got':111 'great':19 'guy':7 'help':121 'input':58 'interest':26 'landscap':117 'learn':11 'liter':110 'look':113 'lot':102 'machin':10 'new':51 'one':66 'part':27 'play':13 'pokemon':14 'previous':65 'process':23 'produc':39 'reward':36,48,104 'screenshot':55 'small':32 'softwar':130 'sort':128 'specif':74 'stuff':134 'sudden':67 'super':132 'system':37 'take':54 'trigger':100 'turn':86 'understand':123 'unexpect':43 'use':9 'video':4 'watch':2 'water':93 'without':105"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://corndog.social/comment/1430879"
+editedAt: DateTimeImmutable @1702486405 {#4298
date: 2023-12-13 17:53:25.0 +01:00
}
+createdAt: DateTimeImmutable @1701388535 {#4299
date: 2023-12-01 00:55:35.0 +01:00
}
} |
|
Show voter details
|
37 |
DENIED
|
ROLE_USER
|
null |
|
Show voter details
|
38 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4242
+user: App\Entity\User {#4181 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: """
These LLMs are basically just IP laundry. Anyone who claims it’s anything more is either buying into the hype or is actively lying to you.\n
\n
EDIT: Stable Diffusion too. It just takes images from its training data and does photoshop on them piecemeal to create a new prompt.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1701359451 {#4236
date: 2023-11-30 16:50:51.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4243 …}
+nested: Doctrine\ORM\PersistentCollection {#4245 …}
+votes: Doctrine\ORM\PersistentCollection {#4247 …}
+reports: Doctrine\ORM\PersistentCollection {#4249 …}
+favourites: Doctrine\ORM\PersistentCollection {#4251 …}
+notifications: Doctrine\ORM\PersistentCollection {#4253 …}
-id: 183820
-bodyTs: "'activ':23 'anyon':8 'anyth':13 'basic':4 'buy':17 'claim':10 'creat':46 'data':38 'diffus':29 'edit':27 'either':16 'hype':20 'imag':34 'ip':6 'laundri':7 'lie':24 'llms':2 'new':48 'photoshop':41 'piecem':44 'prompt':49 'stabl':28 'take':33 'train':37"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.ml/comment/6256940"
+editedAt: DateTimeImmutable @1702480343 {#4237
date: 2023-12-13 16:12:23.0 +01:00
}
+createdAt: DateTimeImmutable @1701359451 {#4238
date: 2023-11-30 16:50:51.0 +01:00
}
} |
|
Show voter details
|
39 |
DENIED
|
edit
|
App\Entity\EntryComment {#4242
+user: App\Entity\User {#4181 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: """
These LLMs are basically just IP laundry. Anyone who claims it’s anything more is either buying into the hype or is actively lying to you.\n
\n
EDIT: Stable Diffusion too. It just takes images from its training data and does photoshop on them piecemeal to create a new prompt.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1701359451 {#4236
date: 2023-11-30 16:50:51.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4243 …}
+nested: Doctrine\ORM\PersistentCollection {#4245 …}
+votes: Doctrine\ORM\PersistentCollection {#4247 …}
+reports: Doctrine\ORM\PersistentCollection {#4249 …}
+favourites: Doctrine\ORM\PersistentCollection {#4251 …}
+notifications: Doctrine\ORM\PersistentCollection {#4253 …}
-id: 183820
-bodyTs: "'activ':23 'anyon':8 'anyth':13 'basic':4 'buy':17 'claim':10 'creat':46 'data':38 'diffus':29 'edit':27 'either':16 'hype':20 'imag':34 'ip':6 'laundri':7 'lie':24 'llms':2 'new':48 'photoshop':41 'piecem':44 'prompt':49 'stabl':28 'take':33 'train':37"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.ml/comment/6256940"
+editedAt: DateTimeImmutable @1702480343 {#4237
date: 2023-12-13 16:12:23.0 +01:00
}
+createdAt: DateTimeImmutable @1701359451 {#4238
date: 2023-11-30 16:50:51.0 +01:00
}
} |
|
Show voter details
|
40 |
DENIED
|
moderate
|
App\Entity\EntryComment {#4242
+user: App\Entity\User {#4181 …}
+entry: App\Entity\Entry {#2413
+user: Proxies\__CG__\App\Entity\User {#1973 …}
+magazine: App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
}
+image: Proxies\__CG__\App\Entity\Image {#1978 …}
+domain: Proxies\__CG__\App\Entity\Domain {#1889 …}
+slug: "Google-Researchers-Attack-Prompts-ChatGPT-to-Reveal-Its-Training-Data"
+title: "Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data"
+url: "https://www.404media.co/google-researchers-attack-convinces-chatgpt-to-reveal-its-training-data/"
+body: """
> ChatGPT is full of sensitive private information and spits out verbatim text from CNN, Goodreads, WordPress blogs, fandom wikis, Terms of Service agreements, Stack Overflow source code, Wikipedia pages, news blogs, random internet comments, and much more.\n
\n
> Using this tactic, the researchers showed that there are large amounts of privately identifiable information (PII) in OpenAI’s large language models. They also showed that, on a public version of ChatGPT, the chatbot spit out large passages of text scraped verbatim from other places on the internet.\n
\n
> “In total, 16.9 percent of generations we tested contained memorized PII,” they wrote, which included “identifying phone and fax numbers, email and physical addresses … social media handles, URLs, and names and birthdays.”\n
\n
Edit: [The full paper that's referenced in the article can be found here](https://arxiv.org/pdf/2311.17035.pdf)
"""
+type: "link"
+lang: "en"
+isOc: false
+hasEmbed: false
+commentCount: 80
+favouriteCount: 364
+score: 0
+isAdult: false
+sticky: false
+lastActive: DateTime @1701712043 {#2418
date: 2023-12-04 18:47:23.0 +01:00
}
+ip: null
+adaAmount: 0
+tags: null
+mentions: null
+comments: Doctrine\ORM\PersistentCollection {#1688 …}
+votes: Doctrine\ORM\PersistentCollection {#1934 …}
+reports: Doctrine\ORM\PersistentCollection {#1965 …}
+favourites: Doctrine\ORM\PersistentCollection {#1396 …}
+notifications: Doctrine\ORM\PersistentCollection {#2439 …}
+badges: Doctrine\ORM\PersistentCollection {#2357 …}
+children: []
-id: 18235
-titleTs: "'attack':3 'chatgpt':5 'data':10 'googl':1 'prompt':4 'research':2 'reveal':7 'train':9"
-bodyTs: "'/pdf/2311.17035.pdf)':134 '16.9':88 'address':109 'agreement':23 'also':61 'amount':48 'articl':127 'arxiv.org':133 'arxiv.org/pdf/2311.17035.pdf)':132 'birthday':117 'blog':17,31 'chatbot':71 'chatgpt':1,69 'cnn':14 'code':27 'comment':34 'contain':94 'edit':118 'email':106 'fandom':18 'fax':104 'found':130 'full':3,120 'generat':91 'goodread':15 'handl':112 'identifi':51,101 'includ':100 'inform':7,52 'internet':33,85 'languag':58 'larg':47,57,74 'media':111 'memor':95 'model':59 'much':36 'name':115 'news':30 'number':105 'openai':55 'overflow':25 'page':29 'paper':121 'passag':75 'percent':89 'phone':102 'physic':108 'pii':53,96 'place':82 'privat':6,50 'public':66 'random':32 'referenc':124 'research':42 'scrape':78 'sensit':5 'servic':22 'show':43,62 'social':110 'sourc':26 'spit':9,72 'stack':24 'tactic':40 'term':20 'test':93 'text':12,77 'total':87 'url':113 'use':38 'verbatim':11,79 'version':67 'wiki':19 'wikipedia':28 'wordpress':16 'wrote':98"
+cross: false
+upVotes: 0
+downVotes: 0
+ranking: 1701362787
+visibility: "visible "
+apId: "https://kbin.social/m/privacy@lemmy.ml/t/665071"
+editedAt: DateTimeImmutable @1702265006 {#1858
date: 2023-12-11 04:23:26.0 +01:00
}
+createdAt: DateTimeImmutable @1701276387 {#2388
date: 2023-11-29 17:46:27.0 +01:00
}
}
+magazine: App\Entity\Magazine {#264}
+image: null
+parent: null
+root: null
+body: """
These LLMs are basically just IP laundry. Anyone who claims it’s anything more is either buying into the hype or is actively lying to you.\n
\n
EDIT: Stable Diffusion too. It just takes images from its training data and does photoshop on them piecemeal to create a new prompt.
"""
+lang: "en"
+isAdult: false
+favouriteCount: 1
+score: 0
+lastActive: DateTime @1701359451 {#4236
date: 2023-11-30 16:50:51.0 +01:00
}
+ip: null
+tags: null
+mentions: [
"@btp@kbin.social"
]
+children: Doctrine\ORM\PersistentCollection {#4243 …}
+nested: Doctrine\ORM\PersistentCollection {#4245 …}
+votes: Doctrine\ORM\PersistentCollection {#4247 …}
+reports: Doctrine\ORM\PersistentCollection {#4249 …}
+favourites: Doctrine\ORM\PersistentCollection {#4251 …}
+notifications: Doctrine\ORM\PersistentCollection {#4253 …}
-id: 183820
-bodyTs: "'activ':23 'anyon':8 'anyth':13 'basic':4 'buy':17 'claim':10 'creat':46 'data':38 'diffus':29 'edit':27 'either':16 'hype':20 'imag':34 'ip':6 'laundri':7 'lie':24 'llms':2 'new':48 'photoshop':41 'piecem':44 'prompt':49 'stabl':28 'take':33 'train':37"
+ranking: 0
+commentCount: 0
+upVotes: 0
+downVotes: 0
+visibility: "visible "
+apId: "https://lemmy.ml/comment/6256940"
+editedAt: DateTimeImmutable @1702480343 {#4237
date: 2023-12-13 16:12:23.0 +01:00
}
+createdAt: DateTimeImmutable @1701359451 {#4238
date: 2023-11-30 16:50:51.0 +01:00
}
} |
|
Show voter details
|
41 |
DENIED
|
edit
|
App\Entity\Magazine {#264
+icon: Proxies\__CG__\App\Entity\Image {#245 …}
+name: "privacy@lemmy.ml"
+title: "privacy"
+description: """
A place to discuss privacy and freedom in the digital world.\n
============================================================\n
\n
Privacy has become a very important issue in modern society, with companies and governments constantly abusing their power, more and more people are waking up to the importance of digital privacy.\n
\n
In this community everyone is welcome to post links and discuss topics related to privacy.\n
\n
### Some Rules\n
\n
- Posting a link to a website containing tracking isn’t great, if contents of the website are behind a paywall maybe copy them into the post\n
- Don’t promote proprietary software\n
- Try to keep things on topic\n
- If you have a question, please try searching for previous discussions, maybe it has already been answered\n
- Reposts are fine, but should have at least a couple of weeks in between so that the post can reach a new audience\n
- Be nice :)\n
\n
### Related communities\n
\n
- [Lemmy.ml libre_culture](https://lemmy.ml/c/libre_culture)\n
- [Lemmy.ml privatelife](https://lemmy.ml/c/privatelife)\n
- [Lemmy.ml DeGoogle](https://lemmy.ml/c/degoogle)\n
- [Lemmy.ca privacy](https://lemmy.ca/c/privacy)\n
\n
### Chat rooms\n
\n
- [Matrix/Element]Dead\n
- [Discord](https://discord.gg/8xfrVjvngh)\n
\n
much thanks to @gary_host_laptop for the logo design :)
"""
+rules: null
+subscriptionsCount: 1
+entryCount: 561
+entryCommentCount: 7684
+postCount: 6
+postCommentCount: 73
+isAdult: false
+customCss: null
+lastActive: DateTime @1729582580 {#274
date: 2024-10-22 09:36:20.0 +02:00
}
+markedForDeletionAt: null
+tags: null
+moderators: Doctrine\ORM\PersistentCollection {#236 …}
+ownershipRequests: Doctrine\ORM\PersistentCollection {#232 …}
+moderatorRequests: Doctrine\ORM\PersistentCollection {#221 …}
+entries: Doctrine\ORM\PersistentCollection {#179 …}
+posts: Doctrine\ORM\PersistentCollection {#137 …}
+subscriptions: Doctrine\ORM\PersistentCollection {#199 …}
+bans: Doctrine\ORM\PersistentCollection {#116 …}
+reports: Doctrine\ORM\PersistentCollection {#102 …}
+badges: Doctrine\ORM\PersistentCollection {#80 …}
+logs: Doctrine\ORM\PersistentCollection {#70 …}
+awards: Doctrine\ORM\PersistentCollection {#1360 …}
+categories: Doctrine\ORM\PersistentCollection {#1792 …}
-id: 85
+apId: "privacy@lemmy.ml"
+apProfileId: "https://lemmy.ml/c/privacy"
+apPublicUrl: "https://lemmy.ml/c/privacy"
+apFollowersUrl: "https://lemmy.ml/c/privacy/followers"
+apInboxUrl: "https://lemmy.ml/inbox"
+apDomain: "lemmy.ml"
+apPreferredUsername: "privacy"
+apDiscoverable: true
+apManuallyApprovesFollowers: null
+privateKey: null
+publicKey: null
+apFetchedAt: DateTime @1729583592 {#268
date: 2024-10-22 09:53:12.0 +02:00
}
+apDeletedAt: null
+apTimeoutAt: null
+visibility: "visible "
+createdAt: DateTimeImmutable @1699780272 {#270
date: 2023-11-12 10:11:12.0 +01:00
}
} |
|
Show voter details
|