https://www.apolloresearch.ai/research/frontier-models-are-capable-of-incontext-scheming/
Nov 18, 2025 - Apollo Research evaluated frontier models for in-context scheming capabilities. We found that multiple frontier models are capable of in-context scheming when...
frontiermodelscapablecontextscheming
https://www.apolloresearch.ai/
Nov 11, 2025 - Apollo Research is focused on reducing dangerous capabilities in advanced AI systems, especially deceptive behaviors. We design AI model evaluations and...
apollo research
https://www.apolloresearch.ai/research/ai-behind-closed-doors-a-primer-on-the-governance-of-internal-deployment/
Nov 18, 2025 - In the race toward increasingly capable artificial intelligence (AI) systems, much attention has been focused on how these systems interact with the public....
behind closed doorsaiprimergovernance