Jake Mendel on X: "It increasingly seems to me like incentives in RL is a bigger determinant of model behavior than generalization from character training or pretraining. I wish more people thought about AI behavior in terms of what RL incentivises. Unfortunately, this mode of behavioural analysis" / X
x.com · saved by 1 readers
It increasingly seems to me like incentives in RL is a bigger determinant of model behavior than generalization from character training or pretraining. I wish more people thought about AI behavior in terms of what RL incentivises. Unfortunately, this mode of behavioural analysis suggests that there…