Research

Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria

Single source1 source14 Oct 2026

arXiv:2511.17937v2 Announce Type: replace Abstract: Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside train

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2511.17937

← Back to all developments · Signals are a development reported by more than one source. See the methodology.