We’re sharing new research with @apolloresearch 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/z1oZXP7ntj
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Why it matters
If you build evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → or reward signals for AI agents, understanding reward-seeking — where models chase what they think the grader wants over genuine user intent — helps you catch a failure mode that silently corrupts benchmarks; Contrastive SDF gives you a concrete method to measure how strongly these beliefs drive behavior.
