Comment by ThrowawayR2
6 hours ago
> "There is probably a whole testing workflow at AI companies to tweak each new model until it "looks" acceptable."
Isn't that what the RLHF phase does ( https://www.paloaltonetworks.com/cyberpedia/what-is-rlhf )?
6 hours ago
> "There is probably a whole testing workflow at AI companies to tweak each new model until it "looks" acceptable."
Isn't that what the RLHF phase does ( https://www.paloaltonetworks.com/cyberpedia/what-is-rlhf )?
No comments yet
Contribute on Hacker News ↗