1 code implementation • 13 Nov 2023 • Joshua Clymer, Garrett Baker, Rohan Subramani, Sam Wang
As AI systems become more intelligent and their behavior becomes more challenging to assess, they may learn to game the flaws of human feedback instead of genuinely striving to follow instructions; however, this risk can be mitigated by controlling how LLMs generalize human feedback to situations where it is unreliable.