Re:RLHF is just barely RL
by digging on Thursday August 08, 2024 @11:58AM
(#41192920)
A human has the ability to contact the PM and say, "This won't work, for $reason," or, "This is going to look really bad in $edgeCase, here are a couple options I've thought of."
There's nothing about AI that makes such operations intrinsically impossible, but they require much more than just the ability to generate working code.
There's nothing about AI that makes such operations intrinsically impossible, but they require much more than just the ability to generate working code.