lemmyshitpost

This magazine is from a federated server and may be incomplete. Browse more on the original instance.

force, in Be safe out there, Atlanta.

The first time I went to Atlanta as a kid I saw someone get shot while I was in a hotel room looking out the window

GrammatonCleric, in Corny
@GrammatonCleric@lemmy.world avatar

It’s like that scene in Requiem For A Dream

404,

My first thought.

We’re all the same aren’t we?

Viking_Hippie, (edited )

We’re all the same aren’t we?

No, we are all individuals! Except for that guy over there points. He’s totally the same.

bruhduh, in Propagandists love this simple trick
@bruhduh@lemmy.world avatar

If it aligns with your political stance that is

Norgur, in this AI thing

It's almost as if the LLMs that got hyped to the moon and back are just word calculators doing stochastic calculations one word at a time... Oh wait...

No, seriously: all they are good for is making things sound fancy.

FinalRemix, (edited )

all they are good for is making things sound fancy.

Ehh, I use NovelAI, and it kind of turns writing into an interactive CYOA game. If I get stuck in a scene and I dunno what to put next, I’ll have a character say or do something, and let the AI go “yeah! And—” like a good improv partner in my voice.

But it’s not a “discussion” or instruct model, so it’s slightly less stupid. Except when it gets written facts wrong that are active in the lorebook and memory, and it ignores them.

Norgur,

NovelAI is one of the uses of such an AI that actually makes sense.

dependencyinjection,

A little reductive.

We use CoPilot at work and whilst it isn’t doing my job for me, it’s saving me a lot of time. Think of it like Intellisense, but better.

If my senior engineer, who I seem like a toddler when compared to can find it useful and foot the bill for it, then it certainly has value.

Norgur,

It's not reductive. It's absolutely how those LLMs work. The fact that it's good at guessing as long as your inputs follow a pattern only underlines that.

QuaternionsRock,

No, seriously: all they are good for is making things sound fancy.

This is the part of your comment is reductive. The first part just explains how LLMs work, albeit sarcastically.

Honytawk, (edited )

If it was only guessing, it would never be able to create a single functioning program. Which it has, numerously.

This isn’t some infinite monkeys on typewriter stuff.

It writes and can check itself if it is correct.

I’ve seen ChatGPT write an entire Website in Wordpress, including setting up a MySQL database for users, by a user stating their wishes vocally in a microphone and then not touching the computer once.

How is that guessing?

Norgur,

No, it does not "check itself". You mixed up "completely random guesses" and stochastically calculated guesses... ChatGPT has.an obscenely large corpus of training data that was further refined by a blatant disregard for copyright and tons and tons of exploited workers in low wage countries, right?

So imagine the topic "setup Wordpress". ChatGPT has just about every article indexed that's on the internet about this. Word for word. So it's able to assign a number to each word and calculate the probability of each word following every other word it scanned. Since WordPress follows a very clear pattern as to how it's set up, those probabilities will be very clear cut.
The details the user entered can be stitched in because ChatGPT can very easily detect variables given the huge amount of data. Imagine a CREATE USER MySQL command. ChatGPTs sources will be almost identical up until it comes to the username which suddenly leads to a drop on certainty regarding the next Word. So there's your variable. Now stitch in the word the user typed after the word "User" and bobs your uncle.

ChatGPT can "write programs" because programming (just as human language) follows clear patterns that become pretty distinct if the amount of data you analyze becomes large enough.

ChatGPT does not check anything it spurts out. It just generates a word and calculates which word is most likely to follow that one.

It only knows which sources of it's training data it should xluse because those were sorted and categorized by humans slaving away in Africa and Asia, doing all the categories by hand.

SkyNTP,

No, seriously: all they are good for is making things sound fancy.

This is the danger though.

If “boomers” are making the mistake of thinking that AI is capable of great things, “zoomers” are making the mistake of thinking society is built on anything more than some very simple beliefs in a lot of stupid people, and all it takes to make society collapse is to convince a few of these stupid people that their ideas are any good.

Cannacheques,

I disagree with the last part. Society and it’s many systems is pretty hard to collapse even if you managed to drug a huge portion of the population, gave them guns and fed them propaganda. Now imagine throwing heaps of people into jail like in Czech, still standing just more useless. Just look at portions of the middle east. The majority of people just get good at being lazy and defer accountability to the most violent assholes who then become dictators, the rest of society then selectively breeds the “dictators”.

If this sounds dystopic consider that what you said lead to what this comment is, which is dumb. Now which is dumber?

Risus_Nex, in Corny

“Now kiss!” (っ˘ڡ˘ς)

bruhduh,
@bruhduh@lemmy.world avatar

Kith

FlyingSquid,
@FlyingSquid@lemmy.world avatar

Do those guys look like they can deepthroat?

can,

They look like they’re willing to try.

instamat, in Never forgetti

Ah, high school

dylanTheDeveloper, (edited ) in They forgot the LGBTQ...
@dylanTheDeveloper@lemmy.world avatar

Louis Armstrong with his brother Lance Armstrong back in 89 both went to the moon. All so you could have smaller computers and political posts like this :/

lseif,

so many things wrong here:

  1. lois armstrong played the trombone
  2. lance armstrong’s real name is buzz aldrin
  3. it was '69, not '98
  4. the moon landing was in no way politicized
  5. i am not using a computer, but a phone
CaptKoala,

I removed and moan as much as the next bloke, but yeah that comment hit me right in the soul (assuming I have one).

ExLisper, in What could have been

Such a tragic story made beautiful by good writing and a bit of compassion. 10/10

Garbanzo, in Try it

I’ll fuck with a dozen corn dogs but I’m not eating the bones, that’s just crazy

Retrograde,
@Retrograde@lemmy.world avatar

True, I prefer boneless corn dogs anyway

merc, in Propagandists love this simple trick

This makes me wonder what would happen if you took the content off some celebrity-focused website like say TMZ but changed the formatting to make it look like New York Times articles.

Like, the “gravitas” of the NY Times politics section with content like “Guess Whose Shirtless Selfie!”

lugal, in Propagandists love this simple trick

Source?

jaschen, in should i??

I dated a very attractive girl once that was very into ddr. But we were very young back then.

dylanTheDeveloper,
@dylanTheDeveloper@lemmy.world avatar

I’m personally a fan of ddr3

Sanyanov,

DDR4 fanboy here

Anti_Iridium,

But we’re on DDR5. Which I can’t afford.

Sanyanov,

Which is why I’m a DDR4 fanboy :P

chicken, in There's story behind this sign

Well, what is it??

DragonTypeWyvern,

Billionaire shot a poor person

chicken,

Source?

DragonTypeWyvern,

The sign

chicken,

ok

airbussy, in The DDD struggle is real

Don’t we all struggle with domain driven design sometimes

DarkMessiah, in this AI thing

Honestly, the best use for AI in coding thus far is to point you in the right direction as to what to look up, not how to actually do it.

DJDarren,

That’s how I use Chat GPT. Not for coding, but for help on how to get Excel to do things. I guess some of what I want to do are fairly esoteric, so just searching for help doesn’t really turn up anything useful. If I explain to GPT what I’ll trying to do, it’ll give me avenues to explore.

TheDoozer,

Can you give an example? This sounds like exactly what I’ve always wanted.

gornius, (edited )

I have a spreadsheet with items with their price and quantity bought. I want to include a discount with multiple tiers, based on how much items have been bought, and have a small table where I can define quantity and a discount that applies to that quantity. Which Excel functions should I use?

Response:

You can achieve this in Excel using the VLOOKUP or INDEX-MATCH functions along with the IF function.

Create a table with quantity and corresponding discounts.

Use VLOOKUP or INDEX-MATCH to find the discount based on the quantity in your main table.

Use IF to apply different discounts based on quantity tiers.

Gork,

Index / Match gang represent. Much more flexible than Vlookup.

TheDoozer,

That’s really cool, I gotta try that in the future. Thanks!

veni_vedi_veni,

It’s shunned upon in the Excel pro scene (shout-out to my boi Makro), but xlookup can be used instead

Baizey,

That’s exactly how I use it (but for more things than excel), it works pretty well as a documentation ‘searcher’ + template/example maker

FrostyTrichs,

Using AI in this way is what finally pushed me to learn databases instead of trying to make excel do tricks it’s not optimal for anyways.

I tried a bunch of iterations of various AI resources and even stuff like the Google Sheets integration and most of them just annoyed me into finding better ways to search for what I was trying to do. Eventually I had to stop ignoring the real problem and pivot to software better optimized for the work I was trying to do with it.

guy,
@guy@lemmy.world avatar

I’ve found it’s best use to me as a glorified auto-complete. It knows pretty well what I want to type before I get a chance to type it. Yes, I don’t trust stuff it comes up with on its own though, then I need to Google it

explodicle,

I think of it as a step between a Google search and bothering actual people by asking for help.

0x4E4F, (edited )

Yeah, that’s about it. I’ve trown buggy code at it, tell it to check it, says it’ll work just fine… scripts as well. You really can’t trust anything that that thing outputs and it’s more than 1 or 2 lines long (hello world examples excluded, they work just fine in most cases).

ninjan,

There is a (non-meme) reason why Prompt Engineer is a real title these days. It takes a measure of skill to get the model to focus on and attempt to solve the right question. This becomes even more apparent if you try to generate a product description where a newb will get something filled with superlative lies and a pro will get something better than most human writers in the field can muster for a much lower cost per text (compared to professional writers, often on par or more expensive than content farms). AI is a great tool, but it’s neither the only tool (don’t hammer in screws) nor is it perfect. The best approach is to let the AI do the easy boiler plate 80% then add that human touch to the hard 20% and at most have the AI prepare the structure / stubs.

0x4E4F,

To be honest, I just gave up on it regarding code. Now I use it mostly for getting info into one place when I know it’s scattered all over the web.

the_sisko,

I’m totally willing to accept “the world is changing and new skills are necessary” but at the same time, are a prompt engineer’s skills transferrable across subject domains?

It feels to me like “prompt engineering” skills are just skills to compliment the expertise you already have. Like the skill of Google searching. Or learning to use a word processor. These are skills necessary in the world today, but almost nobody’s job is exclusively to Google, or use a word processor. In reality, you need to get something done with your tool, and you need to know shit about the domain you’re applying that tool to. You can be an excellent prompt engineer, and I guess an LLM will allow you to BS really well, but subject matter experts will see through the BS.

I know I’m not really strongly disagreeing, but I’m just pushing back on the idea of prompt engineer as a job (without any other expertise).

Cannacheques,

To be fair, in my mind most AI is kind of half baked potential terminator style nightmare fuel for the average person

ninjan,

We’re not talking small organizations here, nor small projects. In those cases it’s true that you can’t “only” do prompt engineering but where I see it is in larger orgs where you bring into the team the know how about how to prompt efficiently, how to do refinement, where to do variable substitution and how, etc etc. The closest analogy is specific tech skills, like say DBs, for a small firm its just something one backend dude knows decently, at a large firm there are several DBAs and they help teams tackle complex DB questions. Same with say Search, first Solr and nowadays Elastic. Or for that matter Networks, in many cases there might be absolutely no one at the whole firm that knows anything more than the basics because you have another company doing it for you.

the_sisko,

The closest analogy is specific tech skills, like say DBs, for a small firm its just something one backend dude knows decently, at a large firm there are several DBAs and they help teams tackle complex DB questions. Same with say Search, first Solr and nowadays Elastic.

Yeah I mean I guess we’re saying the same thing then :)

I don’t think prompt engineering could be somebody’s only job, just a skill they bring to the job, like the examples you give. In those cases, they’d still need to be a good DBA, or whatever the specific role is. They’re a DBA who knows prompt engineering, etc.

ignotum,

Have you looked at the project that spins up multiple LLM “identities” where they are “told” the issue to solve, one is asked to generate code for it, the others “critique” it, it generates new code based on the feedback, then it can automatically run it, if it fails it gets the error message so it can fix the issues, and only once it has generated code that works and is “accepted” by the other identities, it is given back to you

It sounds a bit silly, but it turns out to work quite well apparently, critiquing code is apparently easier than generating it, and iterating on code based on critiques and runtime feedback is much easier than producing correct code in one go

0x4E4F,

Hm… that sounds interesting… a link to this AI?

ignotum,
0x4E4F,

Thanks 👍, on my watch list.

DanVctr,

The software that implements multi agents called ChatDev, it’s significant more capable than one agent working alone. The ability to critique and fix bugs in the code in an iterative process gives a massive step up to the ability of the AI to program.

Granted it might still get in a loop between the programing and testing departments, but it’s a solid step in the right direction.

ignotum,

I was thinking of AutoGPT, but nice to see there are multiple projects taking a crack at this approach

TheBlue22,

100% this yeah.

infamousta,

Yeah, I find it works really well for brainstorming and “rubber-ducking” when I’m thinking about approaches to something. Things I’d normally do in a conversation with a coworker when I really am looking more for a listener than for actual feedback.

I can also usually get useful code out of it that would otherwise be tedious or fiddly to write myself. Things like “take this big enum and write a function that converts the members to human-friendly strings.”

PrMinisterGR,

All the hype are grifters and Google trying to convince people this isn’t just a search engine assistant.

criticalimpact,

Well we need something now that google is absolute dogshit at providing useful results XD Maybe not AI though

Karyoplasma,

Tell ChatGPT you want to do the project as an exercise and that it should not write any pseudocode. It will then give you a high-level breakdown which is usually a decent guide line.

  • All
  • Subscribed
  • Moderated
  • Favorites
  • lemmyshitpost@lemmy.world
  • localhost
  • All magazines
  • Loading…
    Loading the web debug toolbar…
    Attempt #