A New Trick Reveals AI Models’ Inner Thoughts
Wired AI Will Knight August 11, 2026

AI Summary— plain English for professionals
# What This Means for You Researchers have figured out how to peek inside AI models and see what they're "thinking" as they work through problems—essentially reading their step-by-step reasoning. Their findings suggest that some Chinese AI systems may have been trained using American AI models as a starting point, raising questions about AI development practices and competition between countries.
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.
More from Future of AI
Get new guides every week
Real AI income strategies, tool reviews, and plain-English news — free in your inbox.
or enter email



