this post was submitted on 03 Jun 2024
1297 points (96.4% liked)
Technology
59710 readers
4920 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
LLMs have a high coolness-to-code ratio; very cool and not a lot of code. This is the type of thing open source developers are more interested in, so I hope Linux will have some good AI built-in and running locally.
Half of Linux usage is on the text-based command line anyway, just what LLMs are good at.
You are going to allow an LLM to run commands on your system?
Maybe.
Like, if I could type "extract the audio of this video and re-encode it as a medium quality MP3, break up the audio into 30 consecutive tracks" in a shell, and the next line was populated with the appropriate ffmpeg command, but not yet executed, I could quickly look over the command, nothing looks fishy, so I go ahead and run the command.
And it will be optimized for nothing looking fishy, right.
It's no different than what the internet has been doing for us for decades. People tell us commands to run, we use our best judgement, maybe check a couple things, and then run the commands. If the internet suggests a command or a LLM suggests a command, what's the difference?
You could have a command that recommends commands and then you select them on a drop-down list.
Alternatively if the dataset is verified you wouldn't need to worry about it running dangerous commands, since it doesn't know any. Or you could have a list of verified commands that run automatically and any command not on that list requires confirmation.
But this is missing the point that most of the time I know exactly what command I want to run so adding a LLM Is quite useless. The reason so much of linux is still relying on commands is because for a lot of people (myself included) commands are quick and efficient.
Still dangerous. One character (even a space) might make a huge difference. You wouldn't want a hallucinating probability matrix barf out a command and run it only half understanding what it does. By building it yourself, you get a better understanding.
100% agreed here.
What would an ai achieve? The only thing I can think of is a documentation summariser, but that can already be made with current applications independent of linux
It helps make things more self-contained. If a Linux distribution comes with an LLM that knows how to use and tweak the OS and also knows a lot about various programming languages and lots of things in general, that's a big step towards having an OS that can be operated locally without using the internet.
I wouldn't like it if Linux required an internet connection to function, and yet... I've never been able to configure or do much of anything in Linux without referring to the internet.