←back to thread

GPT-5.2

(openai.com)
1019 points atgctg | 1 comments | 11 Dec 25 18:04 UTC | HN request time: 0.201s | source
Show context
xd1936 ◴[11 Dec 25 18:44 UTC] No.46235269[source]▶
> While GPT‑5.2 will work well out of the box in Codex, we expect to release a version of GPT‑5.2 optimized for Codex in the coming weeks.

https://openai.com/index/introducing-gpt-5-2/

replies(2): >>46235378 #>>46241425 #
jstummbillig ◴[11 Dec 25 18:50 UTC] No.46235378[source]▶
> For coding tasks, GPT-5.1-Codex-Max is a faster, more capable, and more token-efficient coding variant

Hm, yeah, strange. You would not be able to tell, looking at every chart on the page. Obviously not a gotcha, they put it on the page themselves after all, but how does that make sense with those benchmarks?

replies(3): >>46235489 #>>46239957 #>>46241609 #
tempaccount420 ◴[11 Dec 25 18:56 UTC] No.46235489[source]▶
Coding requires a mindset shift that the -codex fine-tunes provide. Codex will do all kinds of weird stuff like poking in your ~/.cargo ~/go etc. to find docs and trying out code in isolation, these things definitely improve capability.
replies(1): >>46236235 #
1. dmos62 ◴[11 Dec 25 19:49 UTC] No.46236235[source]▶
The biggest advantage of codex variants, for me, is terseness and reduced sicophany. That, and presumably better adherence to requested output formats.