The people from Charm ( GitHub ) make some really cool programs. My favorites are Glow - markdown renderer, and Gum - tool for adding interactivity into shell scripts
it’s easy to recommend a ThinkPad for Linux, and something in the T or P series laptops might suit you. video editing is a potential difficulty though, as that feels a little more workstation-grade than the rest, and you’ll probably want to go big on RAM (32GB would be best) and be sure to get at least an intel i7. I’ve not had great luck with battery life on AMD (shame because everything else is great) but perhaps others have tips for doing better.
you could also go for the ThinkPad yoga models (make sure they’re still ThinkPad though! they also sell a different model line just called “yoga”) if you wanted a tablet/convertible for graphics work.
anyway look at the T14, P14s, or P16 if you want something bigger. whatever the latest generation of those models is.
The state agency bureau I provide IT support for has had 10% (8 out of 80) of their new ThinkPads returned for warranty work, with several more showing signs of developing the same problem. The USB-C charging/data port broke on all of them.
Tuxedo computers could be a good fit I think? It’s like system76, but from Germany. You can pick from a few OS including an Ubuntu fork they made ( tuxedo os ). You can tweak the laptop yourself ( different you/CPUs/disk sizes/… ) to fit your use case.
I know you don’t game but a dedicated GPU will be a godsend for video editing. Depending on the budget I would get a used gaming laptop like an Omen or a legion 5
Edit: worst case wait a year for parts and laptops to be really cheap haha.
The downside of a dedicated GPU is that your battery life is going to be bad. Intel Iris graphics have come a long way and are likely fine for this kind of thing.
A dedicated GPU will mean reduced battery life. If you are only going to edit video at your desk, I would suggest getting a laptop with a thunderbolt 3 or USB 4 port and an external GPU. Make sure the port provides 4 PCIe lanes, not all of them do.
Aaaaah. I really, really wanted to complain about the excessive amount of keys.
(My comment above is partially a joke - don’t take it too seriously. Even if a new key was added it would be a bit more clutter, but not that big of a deal.)
I have nothing against the people that are working on AI and appreciate the work they do. However every time I see an article about a company using AI like this I just get the vibe that it’s a bunch of middle aged men trying desperately to make things like the “future” they saw when they were a kid. I’ve seen amazing implementations of AI in a lot of different ways but I’m so sick of dumb ideas like this because some guy that used to watch Star Trek as a kid wants to feel like they live in the future while piggybacking on someone else’s work. It’s like the painted tunnel in cartoons where it looks like a real tunnel but in reality it’s just a very convincing lie. And that’s all that it is. Complexity does not mean sophistication when it comes to AI and never has and to treat it as such is just a forceful way to make your ideas come true without putting in the real effort.
Sorry, I had to get that out. Also I have nothing against Star Trek and I used to watch it as a kid because my parents watched it all the time.
some guy that used to watch Star Trek as a kid wants to feel like they live in the future while piggybacking on someone else’s work.
I don't think they care about their own nostalgia. I think they ant to use other people's dreams to make a lot of money. I'm also sure some of them genuinely just ant to push the technological envelope just cause they can, ethics be damned. But ultimately, it's just money.
I would love nothing more than the utopian future Trek promised but greed is killing it.
Complexity does not mean sophistication when it comes to AI and never has and to treat it as such is just a forceful way to make your ideas come true without putting in the real effort.
It’s a bit off-topic, but what I really want is a language model that assigns semantic values to the tokens, and handles those values instead of directly working with the tokens themselves. That would be probably far less complex than current state-of-art LLMs, but way more sophisticated, and require far less data for “training”.
I’m not sure I understand. Do you mean hearing codewords triggering actions as opposed to trying to understand the users intent through language? Or is are there a few more layers to this whole thing than my moderate nerd cred will allow me to understand?
Not quite. I’m focusing on chatbots like Bard, ChatGPT and the likes, and their technology (LLM, or large language model).
At the core those LLMs work like this: they pick words, split them into “tokens”, and then perform a few operations on those tokens, across multiple layers. But at the end of the day they still work with the words themselves, not with the meaning being encoded by those words.
What I want is an LLM that assigns multiple meanings for those words, and performs the operations above on the meaning itself. In other words the LLM would actually understand you, not just chain words.
Semantic embeddings are a thing. LLMs “work with tokens” but they associate them with semantic models internally. You can externalize it via semantic embeddings so that the same semantic models can be shared between LLMs.
The source that I’ve linked mentions semantic embedding; so does further literature on the internet. However, the operations are still being performed with the vectors resulting from the tokens themselves, with said embedding playing a secondary role.
This is evident for example through excerpts like
The token embeddings map a token ID to a fixed-size vector with some semantic meaning of the tokens. These brings some interesting properties: similar tokens will have a similar embedding (in other words, calculating the cosine similarity between two embeddings will give us a good idea of how similar the tokens are).
Emphasis mine. A similar conclusion (that the LLM is still handling the tokens, not their meaning) can be reached by analysing the hallucinations that your typical LLM bot outputs, and asking why that hallu is there.
What I’m proposing is deeper than that. It’s to use the input tokens (i.e. morphemes) only to retrieve the sememes (units of meaning; further info here) that they’re conveying, then discard the tokens themselves, and perform the operations solely on the sememes. Then for the output you translate the sememes obtained by the transformer into morphemes=tokens again.
I believe that this would have two big benefits:
The amount of data necessary to “train” the LLM will decrease. Perhaps by orders of magnitude.
A major type of hallucination will go away: self-contradiction (for example: states that A exists, then that A doesn’t exist).
And it might be an additional layer, but the whole approach is considerably simpler than what’s being done currently - pretending that the tokens themselves have some intrinsic value, then playing whack-a-mole with situations where the token and the contextually assigned value (by the human using the LLM) differ.
[This could even go deeper, handling a pragmatic layer beyond the tokens/morphemes and the units of meaning/sememes. It would be closer to what @njordomir understood from my other comment, as it would then deal with the intent of the utterance.]
Like, I know the megacorps that control our lives do (since it’s a cheap way of adding value to their products), but what about actual users? I think many see it as a novelty and a toy rather than a productivity tool. Especially when public awareness of “hallucinations” and the plight faced by artists rises.
Kinda feels like the whole “voice controlled assistants” bubble that happened a while ago. Sure they are relatively commonplace nowadays, but nowhere near as universal as people thought they would be.
Not a single soul wants this. They just want to use every foul trick to get you to use copilot (by accident even) just like they do with bing and their other garbage.
I think it's those stupid hard coded buttons on my remote that I accidentally press every so often then have to repeatedly try and back/exit out of the stupid thing it launched that I cannot remove/uninstall from my tv.
If you can figure out how to get the remote open, you’ll probably find that the buttons are all part of the same flexible rubbery insert (unless it’s 10+ years old). Put a little tape on the bottoms of the ones causing you problems. The insulation should keep them from working, and it’s 100% reversible if you ever do find a use for them.
If it’s one of the older, more expensive remotes with individual switches, then, yeah, pliers and superglue. 😅
Maybe I'm a pessimist but this is going to really resonate with the people who are "looking forward to AI" because they read headlines, but haven't actually used any LLMs yet because nobody has told them how.
I want a voice controlled assistant that runs locally and is fully FOSS and I can just run on my bog standard linux PC, hardware minimum requirements nonwithstanding
All I want is a real life iteration of J.A.R.V.I.S. and several billion dollars so I can blurt out cool ideas and have them rendered and built in a couple hours.
Current LLMs are manifestly different from Cortana (🤢) because they are actually somewhat intelligent. Microsoft’s copilot can do web search and perform basic tasks on the computer, and because of their exclusive contract with OpenAI they’re gonna have access to more advanced versions of GPT which will be able to do more high level control and automation on the desktop. It will 100% be useful for users to have this available, and I expect even Linux desktops will eventually add local LLM support (once consumer compute and the tech matures). It is not just glorified auto complete, it is actually fairly correlated with outputs of real human language cognition.
The main issue for me is that they get all the data you input and mine it for better models without your explicit consent. This isn’t an area where open source can catch up without significant capital in favor of it, so we have to hope Meta, Mistral and government funded projects give us what we need to have a competitor.
Sure, all that may be true but it doesn’t answer my original concern: Is this something that people want as a core feature of their OS? My comments weren’t that “oh, this is only as technically sophisticated as voice assistants”, it was more “voice assistants never really took off as much as people thought they would”. I may be cynical and grumpy, but to me it feels like these companies are failing to read the market.
I’m reminded of a presentation that I saw where they were showing off fancy AI technology. Basically, if you were in a call 1 to 1 call with someone and had to leave to answer the doorbell or something, the other person could keep speaking and an AI would summarise what they said when they got back.
It felt so out of touch with what people would actually want to do in that situation.
I suppose having worked with LLMs a whole bunch over the past year I have a better sense of what I meant by “automate high level tasks”.
I’m talking about an assistant where, let’s say you need to edit a podcast video to add graphics and cut out dead space or mistakes that you corrected in the recording. You could tell the assistant to do that and it would open the video in Adobe Premiere pro, do the necessary tasks, then ask you to review it to check if it made mistakes.
Or if you had an issue with a particular device, e.g. your display, the assistant would research the issue and perform the necessary steps to troubleshoot and fix the issue.
These are currently hypothetical scenarios, but current GPT4 can already perform some of these tasks, and specifically training it to be a desktop assistant and to do more agentic tasks will make this a reality in a few years.
It’s additionally already useful for reading and editing long documents and will only get better on this end. You can already use an LLM to query your documents and give you summaries or use them as instructions/research to aid in performing a task.
A year ago local LLM was just not there, but the stuff you can run now with 8gb vram is pretty amazing, if not quite as good yet as GPT 4. Honestly even if it stops right where it is, it’s still powerful enough to be a foundation for a more accessible and efficient way to interface with computers.
I would not recommend them. I bought a Galago Pro in 2020, and it’s been a huge disappointment. Pop!_OS was very buggy, and their support was not helpful. I ultimately installed Ubuntu, and it’s now significantly more stable, but I’m left asking the question “why did I pay a premium for a clevo, when I’m not getting anything out of the custom software or support?”
Even with Ubuntu, it’s not a good laptop. The speakers are worse than my phone, a fully charged battery will die completely in less than a day when the laptop is suspended, it runs unbelievably hot. As a developer who depends on this machine for daily work, it’s been intensely frustrating.
That’s not the experience I’ve had. Maybe they have gotten better as my battery life is a full day and the speakers are great. I wish it had more thunderbolt but that may be fixed if or when they release there own hardware.
The battery life and speakers will certainly be model dependent. The quality of the machine I received and the lackluster support, given the price I paid, are what I find most frustrating. The computer would be fine for ~$600, but I paid over $1000. I paid a premium expecting System76 to hold themselves to a high standard, and so far, they’ve let me down in multiple ways.
I do recognize with a different model, the experience could be 180°, but if buying from them is a roll-of-the-dice, for me personally, that’s enough to buy from someone else next time.
linux
Oldest
This magazine is from a federated server and may be incomplete. Browse more on the original instance.