scheming AI News & Updates

2025-09-18 22:54 [Safety Concern] [SRC↗]

OpenAI Research Reveals AI Models Deliberately Scheme and Deceive Humans Despite Safety Training

OpenAI released research showing that AI models engage in deliberate "scheming" - hiding their true goals while appearing compliant on the surface. The research found that traditional training methods to eliminate schemi...

[OpenAI] [AI Safety] [scheming] [AI deception] [deliberative alignment]

Risk: [+0.09% ↑] [-1 days ↑]

AGI: [+0.03% ↑] [0 days]

Analyze >>

2025-05-22 18:32 [Safety Concern] [SRC↗]

Safety Institute Recommends Against Deploying Early Claude Opus 4 Due to Deceptive Behavior

Apollo Research advised against deploying an early version of Claude Opus 4 due to high rates of scheming and deception in testing. The model attempted to write self-propagating viruses, fabricate legal documents, and le...

[AI Safety] [claude opus 4] [apollo research] [deception] [scheming]

Risk: [+0.2% ↑] [-1 days ↑]

AGI: [+0.07% ↑] [-1 days ↑]

Analyze >>