A New Trick Reveals AI Models’ Inner Thoughts
Researchers have found a way to uncover the reasoning steps of advanced AI models like Claude, GPT, and Gemini. This could help improve transparency and reveal insights into how these systems work. The discovery also suggests some Chinese AI may be trained on leading US models, offering a glimpse into global AI development.
Computer scientists recently discovered a way to extract the hidden “thinking” that frontier AI models perform as they work through complex problems.
Wired
