Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
nl
39 days ago
|
parent
|
context
|
favorite
| on:
Unrolling the Codex agent loop
I think Codex is probably marginally stronger than Opus in my testing.
But it's much much worse at writing issues than Claude models.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
But it's much much worse at writing issues than Claude models.