The kernel policy seems to be what I think it is, since LLM slop patches have been merged. Edit: I call it “slop” since it’s LLM code, and I’m aware some use that word differently.
I find it slightly contradictory to delete code due to hidden bugs on the one end, then insert LLM code at the other rather than hand-craft the code to avoid hidden bugs better.
I feel the term slop is being overused to cover anything an LLM has touched. If I ask an agent to re-read a mail thread for me and apply the changes to my tree to review is that slop? Would you feel better about it if I copy and paste from email to code in my editor?
I’ve just been doing a bunch of bug triage which was mostly driven by the agent although I checked the issues where it had commented. Was that slop? Ironically a lot of the issues where AI generated although for the most part more complete than a lot of the purely human submissions we get. Are those bug reports slop? What about the poorly drafted human ones?
The studies about hidden errors don’t really care about how “slop” the code looks, as far as I understand them. That’s why LLM code is kind of dangerous.
I’m saying if their policy is to accept AI code, which the link seems to demonstrate that it is, the rate of future hidden errors in the kernel code is likely going to go up. This is what all the studies are saying, including those involving competent coders.
I heard it’s alright for games and many apparently work. Sadly, FreeBSD simply doesn’t seem to have drivers for a lot of hardware that I’m using. And as far as I know, they don’t have an LLM policy yet (so they could still come out in favor of it).
The kernel policy seems to be what I think it is, since LLM slop patches have been merged. Edit: I call it “slop” since it’s LLM code, and I’m aware some use that word differently.
I find it slightly contradictory to delete code due to hidden bugs on the one end, then insert LLM code at the other rather than hand-craft the code to avoid hidden bugs better.
How is that patch sloppy?
I feel the term slop is being overused to cover anything an LLM has touched. If I ask an agent to re-read a mail thread for me and apply the changes to my tree to review is that slop? Would you feel better about it if I copy and paste from email to code in my editor?
I’ve just been doing a bunch of bug triage which was mostly driven by the agent although I checked the issues where it had commented. Was that slop? Ironically a lot of the issues where AI generated although for the most part more complete than a lot of the purely human submissions we get. Are those bug reports slop? What about the poorly drafted human ones?
The studies about hidden errors don’t really care about how “slop” the code looks, as far as I understand them. That’s why LLM code is kind of dangerous.
Are you saying that AI slop is bad in those (counts) 4 removed lines of code?
I’m saying if their policy is to accept AI code, which the link seems to demonstrate that it is, the rate of future hidden errors in the kernel code is likely going to go up. This is what all the studies are saying, including those involving competent coders.
Hm… How well does FreeBSD run games? It still uses WINE and Proton, right?
I heard it’s alright for games and many apparently work. Sadly, FreeBSD simply doesn’t seem to have drivers for a lot of hardware that I’m using. And as far as I know, they don’t have an LLM policy yet (so they could still come out in favor of it).
Your making a big assumption extrapolating from one particular study involving Java code and a static analyser.
deleted by creator
You should look up the genetic fallacy. And using phrases like “hand-craft code” make you look stupid.