Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
EugeneOZ
3 months ago
|
parent
|
context
|
favorite
| on:
RLHF is just barely RL
TDD approach could play the RL role.
jgalt212
89 days ago
[–]
But what makes you think the ai generated tests will correctly represent the problem at hand?
Consider applying for YC's W25 batch! Applications are open till Nov 12.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
