Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
anshumankmr
on Aug 8, 2024
|
parent
|
context
|
favorite
| on:
RLHF is just barely RL
Unless if it takes maximizing code coverage as the objective and starts deleting failed test cases.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: