Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
mjburgess
3 months ago
|
parent
|
context
|
favorite
| on:
Building more with GPT-5.1-Codex-Max
Given that its likely this sort of SVG output has been RLHF special-cased, I think it's time we move past this benchmark.
simonw
3 months ago
[–]
I don't think it's invalid yet. Those pelicans still kind of suck!
https://simonwillison.net/2025/Nov/13/training-for-pelicans-...
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
