Press Space to continue
RLHF optimizes models to tell humans what they want to hear
Press Space to continue
Jev creator @CompleteSkeptic on why RLHF is guaranteed to disappoint - because it tells you what you want to hear. we want to automate everything and yet our models are literally tuned to optimize for human feedback. https://x.com/aiDotEngineer/status/21014…
@CompleteSkepticQuoted post unavailable hereOpen on X
View
open on x · 1 viewViews and clicks count once per visitor per day. Clicks are opens of this post on X.