Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
thethimble
28 days ago
|
parent
|
context
|
favorite
| on:
GPT-5.3-Codex
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.
helloplanets
28 days ago
|
next
[–]
He wasn't saying that both of the models suck, but that the heuristics for measuring model capability suck
AstroBen
28 days ago
|
prev
[–]
..huh?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
With the right scaffolding these models are able to perform serious work at high quality levels.