Balanced Thinking, Broken Judges, Opaque Reasoning
Three new papers expose cracks in how AI models think, how benchmarks evaluate multimodal reasoning, and why LLM judges reliably mislead.
Reasoning models
Reasoning Models Can't Hide Their Thinking - OpenAI Study
OpenAI's CoT-Control benchmark shows frontier reasoning models score 0.1-15.4% at steering their own chain of thought - a result the company frames as good news for AI oversight.
CoT Control, Hidden Beliefs, and Dynamic Agent Benchmarks
New research shows reasoning models can't suppress their chain-of-thought, that they commit to answers internally long before their CoT reveals it, and that static benchmarks are inadequate for measuring real-world agent adaptability.
AI Models Can Now Jailbreak Other AI Models Autonomously - 97% Success Rate, No Human Involved
Researchers from Stuttgart and ELLIS Alicante gave four reasoning models a single instruction - 'jailbreak this AI' - and walked away. The models planned their own attacks, adapted in real time, and broke through safety guardrails 97.14% of the time across 9 target models.
