Frontier Models are Capable of In-context Scheming(arxiv.org)10 points·by trott·2 yıl önce·1 commentsarxiv.orgFrontier Models are Capable of In-context Scheminghttps://arxiv.org/abs/2412.049841 commentsPost comment[–]abrichr·2 yıl öncereplyhttps://arxiv.org/abs/2412.04984> Our findings demonstrate that frontier models now possess capabilities for basic in-context scheming [covertly pursuing misaligned goals], making the potential of AI agents to engage in scheming behavior a concrete rather than theoretical concern.
> Our findings demonstrate that frontier models now possess capabilities for basic in-context scheming [covertly pursuing misaligned goals], making the potential of AI agents to engage in scheming behavior a concrete rather than theoretical concern.