How to Use AI for Linux Kernel Development
This is about using AI for Linux kernel development, though most tips can apply elsewhere.
I know, I know. AI is quite polarizing in today’s world, to say the least. I will be addressing ethics later. But for now, let’s focus on the tech.
AI is useful because it prototypes fast, multitasks well, and gives you something to work off of instead of making you start from zero. Do I think it replaces…
Read more: https://logicalerzor.codeberg.page/blog/ai-kernel-development/
Alternate version:
Step 1: Don’t.
Another is that once the context window resets, it often loses the information it was working from. If you want a long term maintainer for your code base, it’s better to train up junior engineers so that they one day would become experts on the code base that you or your business is reliant on. But the economy does not usually care about the distant future as much as the now.
Strewth*
*Australian for ain’t that the truth (literally ‘God’s truth’)
I like that you do discuss the ethics in your article, shame you it came across as “not a problem now” in your post
It’s just the way it was cut, in the context of the article “that’s for later” just means later in the article, cut from the article it looks like something you’re not going to cover
I’m not sure how you avoid it other than rewriting the lede to only talk about the main point.
@psud ohhh gotcha yeah, that’s something i noticed too reading the comments
i was hoping that it would be a good hook to get people to read the article, but seems to have caused a knee jerk reaction instead. i wouldve posted the entire article here, but unfortunately on mastodon im limited to 500 chars :(
i might have to rethink how i present my hooks in the future. regardless, thanks again for reading and giving ur thoughts! :)
‘ethics later’ lmfao so on point
How about not using AI for anything? Negative impacts overweigh use. Use ML (as in predictive typing) and call it a day. Don’t replace your brain with a slopmachine
Mentioning A.I. for programming on the fediverse and for the Linux Kernel no less? You’re heading in a world of pain my friend. Good luck!
@Franconian_Nomad hehe lol thanks
most people aren’t even going to read the post in its entirety and comment on a knee jerk reaction (already getting some which is always amusing). those comments aren’t worth addressing tbh
but overall i think this is a useful article as it tries to tow a pragmatic line. plus im fine with challenging my thinking, and if anyone has a useful comment worth considering, im open to it
I like the blog post for the most part. Seems like a nuanced opinion about A.I. Can’t really say much about the programming part - I’m not a programmer.
@Franconian_Nomad thanks for reading! :)
@Logical_Error @linux No, you cannot just ignore the ethics. It does not work that way.
Fine exploration, but I don’t think we have even scratched the surface yet in regards to how creative we can become. In …let’s say, 1 year, you can create your own kernel/OS from scratch if you want to. No more proprietary drivers needed, all distributed/federated systems integrated into a full net v2, etc…
[politics coming up] AI suddenly gives everyone super powers, and while the Epstein class have the best gear, the people have combined compute to beat them. Unfortunately, too many are reacting with knee-jerk anger on the tool, or if it’s ‘intelligent’ or not, and can’t see that we need to change a dead-weigh ideology that are the root cause of the AI ‘problems’. They really should use some time exploring how they can use AI to steer society in a less harmful direction where rich psychopaths can’t set the direction for everyone else, and where we are not dependent on corporate psychos, ‘copyright’, wage-slavery jobs and similar idiotic patches to keep this ideological garbage barge floating.
In one year, we’ll all be waiting for your own custom kernel and OS. We definitely need more competition in the space.
They really should use some time exploring how they can use AI to steer society in a less harmful direction where rich psychopaths can’t set the direction for everyone else
The current AI hype train is exactly what steers society in the direction opposite of what you seem to want. It gives companies an excuse to fire people without taking accountability, and it gives employers an excuse to try to cut wages.
If it were as powerful as you seem to be implying, it would make software devs some of the most valuable workers on the planet. One dev would be capable of doing what entire teams were capable of before. Everyone would want to hire all the devs on the planet and churn out software at an accelerating pace to try to overtake all their competitors. Do you feel that software devs are, in fact, that valuable? Because I just see people getting fired, pay being cut, and workloads increasing to abusive levels.
