alt Hacker News> but how about you and the team who will eventually read and do code review.
Why are you reviewing AI code in detail? Do you also review the assembly output of GCC line by line?
Replies
For instructions you really care about, yes of course you review the assembly output! Usually when you're doing SIMD or want to check atomics are doing what you expect.
I can’t remember the last time GCC emitted code that just flat out called the wrong function. If it did that occasionally, I would review it.
Come on, this is a take we expect from a 1st grader!
Gcc makes maybe 1 mistake ever 2 billion emissions. LLMs make 1 mistake ever 3rd emission.
No, because GCC doesn't randomly fuck up the assembly generation (much less on a fairly frequent basis the way LLMs do). If it did, you bet I'd be reviewing the assembly line by line, or decline to use such a poorly performing tool (as I have with LLMs).
Compilers like GCC are deterministic and the source code already fully defines the behavior. LLMs are non-deterministic and will accept ambiguity, filling in details where you haven’t. These sorts of comparisons aren’t really fair.
In the case of writing, it’s like hiring someone to write a book for you vs. hiring someone to translate a book you wrote into another language. In the first case, you didn’t really define the message for readers, whereas in the second case you did, and the translator is converting that same message for another audience to consume.