←back to thread

Using LLMs at Oxide

(rfd.shared.oxide.computer)
694 points steveklabnik | 1 comments | 07 Dec 25 01:17 UTC | HN request time: 0.215s | source
Show context
hexo ◴[07 Dec 25 08:41 UTC] No.46180184[source]▶
"LLMs are amazingly good at writing code" that one was good. I cant stop laughing.
replies(2): >>46180429 #>>46184091 #
1. leecommamichael ◴[07 Dec 25 18:58 UTC] No.46184091[source]▶
I agree with your sentiment, but I do find it amazing that the underlying techniques of inference can emit code that is as apparently coherent as it is. (This does not imply actual coherence.)