logoalt Hacker News

thethimbleyesterday at 7:16 PM2 repliesview on HN

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.


Replies

helloplanetsyesterday at 7:34 PM

He wasn't saying that both of the models suck, but that the heuristics for measuring model capability suck

AstroBenyesterday at 7:17 PM

..huh?