Hacker News new | ask | show | jobs
by thethimble 141 days ago
Speak for yourself. I've been insanely productive with Codex 5.2.

With the right scaffolding these models are able to perform serious work at high quality levels.
2 comments
helloplanets 141 days ago
He wasn't saying that both of the models suck, but that the heuristics for measuring model capability suck
link
AstroBen 141 days ago
..huh?
link