LLMs make slop code faster than humans can meaningfully review. If you make LLMs the only review layer, then slop gets through because they have similar biases. Stop making slop.
Cool assumption. But pretty sure it’s not how things work at all but sounds great…
What actually happens is that you have a long list of multiple maintainers reviewing , and multiple branches for testing, and multiple layers of review too.
“AI bad. AI do bad thing. Let’s point and laugh at AI doing bad thing to delegitimize the technology in the public’s eyes.”
Meanwhile, at work, I interact with coding agents on a regular basis, and the results are pretty good. Then it goes through a local blind review by a more powerful agent, get pushed out to the company’s code review agent, which is designed to be as critical as possible, check the ticket details, make sure everything matches what the design plan says. Depending on the repo, it might even go through an extra security review.
Then, because we aren’t fucking stupid, it goes through the standard code review process by real developers. Sometimes they still find something, sometimes the agent code reviews found way more than a human can. Overall, I trust the current process over our previous one, where some guy spends barely two minutes looking at the code, rubberstamps it, and then QA discovers a few bugs that need fixing, because the damn code review wasn’t as through and critical as it should have been.
AI bad. Bugs never occurred when human built code. We had to come up with a completely new term, unknown in programming before, called “race condition”.
That’s what code review is for lol.
Where is the story here?
LLMs make slop code faster than humans can meaningfully review. If you make LLMs the only review layer, then slop gets through because they have similar biases. Stop making slop.
Cool assumption. But pretty sure it’s not how things work at all but sounds great…
What actually happens is that you have a long list of multiple maintainers reviewing , and multiple branches for testing, and multiple layers of review too.
https://www.kernel.org/doc/html/next/process/maintainers.html . See that long list of maintainers for a start.
The actual policy is that everything ends up getting reviewed by a human. If I post a patch, it doesn’t go straight to master
If it’s not being properly tested and maintained, it gets dropped irrespective of what it is (remember devfs?)
Also, I’m not sure about the kernel specifically, but on projects I submitted code to, they often wanted complex patches broken down if possible.
XZ Utils made it past all those checks with malicious code from a human.
If they’d been more careful with their tarball commits it probably would have made it into the final and commercial distros.
It made into Homebrew for instance.
“AI bad. AI do bad thing. Let’s point and laugh at AI doing bad thing to delegitimize the technology in the public’s eyes.”
Meanwhile, at work, I interact with coding agents on a regular basis, and the results are pretty good. Then it goes through a local blind review by a more powerful agent, get pushed out to the company’s code review agent, which is designed to be as critical as possible, check the ticket details, make sure everything matches what the design plan says. Depending on the repo, it might even go through an extra security review.
Then, because we aren’t fucking stupid, it goes through the standard code review process by real developers. Sometimes they still find something, sometimes the agent code reviews found way more than a human can. Overall, I trust the current process over our previous one, where some guy spends barely two minutes looking at the code, rubberstamps it, and then QA discovers a few bugs that need fixing, because the damn code review wasn’t as through and critical as it should have been.
AI bad. Bugs never occurred when human built code. We had to come up with a completely new term, unknown in programming before, called “race condition”.