Comment by fzzzy
18 days ago
Hopefully some rlhf-using companies will realize saying "I don't know" is important and start instructing the humans giving feedback to prefer answers that say I don't know over wrong answers.
18 days ago
Hopefully some rlhf-using companies will realize saying "I don't know" is important and start instructing the humans giving feedback to prefer answers that say I don't know over wrong answers.
No comments yet
Contribute on Hacker News ↗