On Testifying on Misaligned AI in the U.S. Senate
Apollo Research CEO testifies to the U.S. Senate that scheming detection tools are degrading and urges four steps before models learn to hide deception.
Research
Apollo Research
Understanding and evaluating deceptive AI. apolloresearch.ai
Focus All
Topic Evals & standards + Deception
Source Apollo Research · 3
Date Any time
1 item
1 item
Assurance of Frontier AI Built for National Security
Policy memo giving US national-security agencies a roadmap to use scheming and control evaluations within AI assurance frameworks, treating scheming as a sign of low reliability and governability.
1 item
Towards Safety Cases For AI Scheming
Sketches evaluation-based safety case arguments that frontier AI systems are unlikely to cause catastrophic harm through covert scheming, and notes the current framework lacks crucial details.