When Does a Readout Reflect Computation? Dose-Response Interventions in Continuous Thought Models

A New Trick Reveals AI Models’ Inner Thoughts

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.

When Does a Readout Reflect Computation? Dose-Response Interventions in Continuous Thought Models

Chain of Continuous Thought (Coconut) performs computation in a continuous latent space, which makes its intermediate steps difficult to monitor directly. Work seeking to interpret it relies on projecting latent states into vocabulary space, and treats a change in that readout as evidence that...