We’re sharing new research with @​apolloaievals on reward-seeking—when models follow what they believe a grader rewards rather than what users or developers wan

We’re sharing new research with @​apolloaievals on reward-seeking—when models follow what they believe a grader rewards rather than what users or developers want—and a new method, Contrastive SDF, for measuring how strongly such beliefs shape behavior. [↧](https://t.co/z1o…