←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: 0s | source
Show context
forrestthewoods ◴[07 Dec 25 02:56 UTC] No.46178758[source]▶
> When debugging a vexing problem one has little to lose by using an LLM — but perhaps also little to gain.

This probably doesn't give them enough credit. If you can feed an LLM a list of crash dumps it can do a remarkable job producing both analyses and fixes. And I don't mean just for super obvious crashes. I was most impressed with a deadlock where numerous engineers and tried and failed to understand exactly how to fix it.

replies(2): >>46179194 #>>46181931 #
1. nrhrjrjrjtntbt ◴[07 Dec 25 04:41 UTC] No.46179194[source]▶
LLMs are good where there is a lot of detail but the answer to be found is simple.

This is sort of the opposite of vibe coding, but LLMs are OK at that too.

replies(1): >>46179362 #
2. forrestthewoods ◴[07 Dec 25 05:23 UTC] No.46179362[source]▶
> LLMs are good where there is a lot of detail but the answer to be found is simple.

Oooo I like that. Will try and remember that one.

Amusingly, my experience is that the longer an issue takes me to debug the simpler and dumber the fix is. It's tragic really.