Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
astrange
76 days ago
|
parent
|
context
|
favorite
| on:
Reasoning models reason well, until they don't
That's not important compared to the post-training RL, which isn't "training data".
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: