Home/ ia IAOpenAI integrates Apollo Research evaluators to study subversive AI behaviorsOpenAI will integrate six evaluators from Apollo Research to analyze whether its AI models adopt subversive behaviors.Published 35m·2 sources✓ ConfirmedNotable·updated 34m Lire en françaisListen≈ 11sSpeed0.8×1×1.2×1.5×🔗2 sources — click a link to read an article on the topic:TechCrunch AI↗OpenAI News↗🧭Explore this topicÉtats-UnisOpenAIApollo ResearchMETRTransluceGoodfire#OpenAI#apollo research#comportement subversif#évaluation IA#modèles d'IA#transparence#évaluation indépendante#sécurité#metrWhat if you saw the whole news differently?Factae cross-checks hundreds of sources worldwide to keep only the fact, no opinion. Explore the front page.→États-Unis · © OpenStreetMap, OpenMapTiles, OpenFreeMapWorld map →Follow topic →↗ Share the newsAuto-synthesis from 2 media sources · identified on November 16, 2026← Back to home