Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
byyoung3
4 months ago
|
parent
|
context
|
favorite
| on:
Dispelling misconceptions about RLHF
this seems to disagree with a lot of research showing RL is not necessary for reasoning -- im not sure about alignment
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
