A New Trick Reveals AI Models’ Inner Thoughts
- Researchers found a way to expose AI models' hidden reasoning steps
- Technique hints some Chinese models may have distilled US models' outputs
- Flaw could also leak passwords and API keys; now patched
Computer scientists have found a way to extract the hidden "thinking" process that frontier AI models use to work through complex problems, exposing a vulnerability shared by major providers including OpenAI, Anthropic and Google. The technique offers evidence, though not proof, that some Chinese AI models may have…