←back to thread

Using LLMs at Oxide

(rfd.shared.oxide.computer)
694 points steveklabnik | 2 comments | 07 Dec 25 01:17 UTC | HN request time: 0.001s | source
Show context
philippta ◴[07 Dec 25 09:25 UTC] No.46180367[source]▶
> LLM-generated code should not be reviewed by others if the responsible engineer has not themselves reviewed it.

To extend that: If the LLM is the author and the responsible engineer is the genuine first reviewer, do you need a second engineer at all?

Typically in my experience one review is enough.

replies(3): >>46180391 #>>46180456 #>>46181202 #
1. ares623 ◴[07 Dec 25 09:42 UTC] No.46180456[source]▶
Yeesss this is what I’ve been (semi-sarcastically) thinking about. Historically it’s one author and one reviewer before code gets shipped.

Why introduce a second reviewer and reduce the rumoured velocity gained by LLMs? After all, “it doesn’t matter what wrote the code” right.

I say let her rip. Or as the kids say, code goes brrr.

replies(1): >>46183931 #
2. sevensor ◴[07 Dec 25 18:39 UTC] No.46183931[source]▶
I disagree. Code review has a social purpose as well as a technical one. It reinforces a shared understanding of the code and requires one person to assure another that the code is ready for review. It develops consensus about design decisions and agreement about what the code is for. With only one person, this is impossible. “Code goes brrr” is a neutral property. It can just as easily take you to the wrong destination as the right one.