Comment by rvnx
2 years ago
Probably not "hard coded" in the literal way, but instead, if the model is using RLHF, they could thumbs up the answer.
2 years ago
Probably not "hard coded" in the literal way, but instead, if the model is using RLHF, they could thumbs up the answer.
No comments yet
Contribute on Hacker News ↗