←back to thread

Coding with LLMs in the summer of 2025 – an update

(antirez.com)
600 points antirez | 1 comments | 20 Jul 25 11:04 UTC | HN request time: 0s | source
Show context
delduca ◴[20 Jul 25 18:31 UTC] No.44627934[source]▶
I have a good example of how sometimes AI/LLM can write very very inefficient code: https://nullonerror.org/2025/07/12/ai-will-replace-programme...
replies(1): >>44628108 #
dawnerd ◴[20 Jul 25 18:49 UTC] No.44628108[source]▶
Similarly, AI is really bad at code golf. You’d think it would be great, able to know all the little secrets but nope. It needs verbose code.
replies(1): >>44628325 #
1. verbify ◴[20 Jul 25 19:08 UTC] No.44628325[source]▶
I wonder what fine tuning an LLM on code golf examples would produce.