On: Large language models develop novel social biases through adaptive exploration

[tptacek]

Humanity hates it among other reasons because it's very probably false.

[threethirtytwo → tptacek]

True. But if it tells the cold hard truth we will also hate it and believe it is lying.

It needs to be trained to give us what we want to hear. What we perceive as truth is often far from the actual ground truth.

Ironically the reinforcement training is already training it to give us exactly what we want to hear.