Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
hackerlight
54 days ago
|
parent
|
context
|
favorite
| on:
Training Language Models to Self-Correct via Reinf...
P(correct) doesn't go down with token count if you have self-correction. It can actually go up with token count.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: