Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on The Darwinian argument for worrying about AI. Parent comment
Reinforcement learning from human feedback (RLHF) makes models dumber and less capable but more compliant.
Meanwhile, high quality synthetic training data (generated by AI) makes models smarter and more capable.
RLHF and human sourced training data is not the ceiling of training intelligent systems, it's the baseline-- the floor.
There are no comments on this comment yet.
Reinforcement learning from human feedback (RLHF) makes models dumber and less capable but more compliant.
Meanwhile, high quality synthetic training data (generated by AI) makes models smarter and more capable.
RLHF and human sourced training data is not the ceiling of training intelligent systems, it's the baseline-- the floor.