News for hackers. Stuff that matters.
Re:GPT-5.4 by cperciva on Thursday March 05, 2026 @08:40PM (#47269739)
Yeah, I would definitely characterize it as an instruction following problem. After a few more round trips I got it to admit that "my earlier passes leaned heavily on build/tests + targeted reads, which can miss many “deep” bugs that only show up under specific conditions or with careful semantic review" and then asking it to "Please do a careful semantic review of files, one by one." started it on actually reviewing code.

Mind you, the bugs it reported were mostly bogus. But at least I was eventually able to convince it to try.

There are no comments on this comment yet.