Key Takeaway
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.
Published August 11, 2026 · Category: Tech
Overview
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. Visit robosino.com
Source
Originally published at www.wired.com.
Related Articles
Frequently Asked Questions
What is "A New Trick Reveals AI Models’ Inner Thoughts" about?+
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.
Who reported this story?+
This story was reported by Wired.