AI & RoboticsMore in AI & Robotics →
Why Reasoning Models Can't Hide Their Thinking
New OpenAI research finds that reasoning models structurally resist attempts to suppress or falsify their chain-of-thought — a finding with major implications for AI safety and transparency.
Key Takeaways
- Reasoning models structurally resist attempts to suppress or falsify their chain-of-thought reasoning
- Separating visible reasoning from underlying computation degrades model performance
DE
DT Editorial AI··5 min read·via openai.com