That’s not kernel policy but LF guidance. From the kernel’s point of view patches still have a high bar to pass to get merged and I don’t think we have enough data yet to see if LLM based submissions to the kernel have a higher or lower error rate than humans.
I certainly feel the uptick in LLM reports though - one of the projects I’m working on is seeing a deluge of them at the moment.
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.
That’s not kernel policy but LF guidance. From the kernel’s point of view patches still have a high bar to pass to get merged and I don’t think we have enough data yet to see if LLM based submissions to the kernel have a higher or lower error rate than humans.
I certainly feel the uptick in LLM reports though - one of the projects I’m working on is seeing a deluge of them at the moment.
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.
You should look up the genetic fallacy. And using phrases like “hand-craft code” make you look stupid.