A New Trick Reveals AI Models’ Inner Thoughts - Peer2Peer

A New Trick Reveals AI Models’ Inner Thoughts

Aug 11, 2026

Researchers devised a way to extract “reasoning traces” from Claude, GPT, and Gemini. What they found, they say, indicates that some Chinese AI may be trained on leading US models.

https://www.wired.com/story/a-new-trick-reveals-ai-models-inner-thoughts/

Respond, make new discussions, see other discussions and customize your news...
Log in.

To add this website to your home screen:

1. Tap

2. Select 'Add to Home screen' or 'Install app'.

3. Follow the on-scrren instructions.

Terms of Service