A New Trick Reveals AI Models’ Inner Thoughts

Computer scientists recently discovered a way to extract the hidden “thinking” that frontier AI models perform as they work through complex problems.

The findings provide some evidence—although not conclusive proof—that certain Chinese models may have been trained by “distilling” reasoning information from US models that was supposedly hidden because of how closely some of their thinking or reasoning patterns seem to match. The researchers have also demonstrated that the method could be used to recover personal information, like passwords and API keys, from a model’s inner reasoning, although this vulnerability has been fixed.

“All major frontier model providers we tested share this vulnerability,” says Alexander Panfilov,⁩ a computer scientist at University of Tübingen in Germany who was involved with the work. “It can lead to personal information leakage, and it enables large-scale reasoning distillation attacks.”

Panfilov and colleagues from the University of Tubingen, the Max Planck Institute, the AI safety institute MATS Research, and the security company Snyk identified the same issue with frontier models from OpenAI, Anthropic, and Google that are accessed via an application programming interface or API.

In a paper laying out the work, the researchers show that the open-weight or downloadable Chinese model Kimi K3 from Moonshot AI produces a strikingly similar output to the hidden reasoning traces—the written-out reasoning steps involved in solving a problem—of Claude Opus 4.8 and GPT 5.6 Sol for certain prompts. Despite the similarities, they note that the work “cannot causally establish distillation.” They found that two other open-weight models, China’s DeepSeek and Inkling from the US company Thinking Machines, did not exhibit this kind of reasoning similarity with Claude Opus.

Moonshot AI and Z.ai did not respond to a request for comment by time of publication.

Distillation is a well-established, widely used technique for efficiently copying the capabilities of existing models over to new ones, and is especially common in the development of open-weight or fully downloadable models.

Lately, however, distillation has become a controversial topic, because of claims that Chinese AI companies use it to essentially copy the best US models. In February, OpenAI told US lawmakers that DeekSeek seemed to have copied one of its models to build a reasoning model called R1. In June, Anthropic told lawmakers that Alibaba had systematically distilled its models in order to build its own, called Qwen.

There’s no indication that Chinese AI companies used this specific technique to distill US-based AI models. But Panfilov and collaborators say that using their method would make it possible to distill more information from closed models than previously realized.

Mini-Me Models

Advanced AI models solve difficult problems by breaking them into constituent parts that are analyzed in turn in a kind of artificial reasoning or “chain of thought.” Companies tend to keep a proprietary model’s reasoning secret to prevent others from using them to train new ones. However, they typically also send an encrypted version of that reasoning to a user’s computer in a way that offloads some computation.

The researchers’ attack relies on the fact that most AI companies also provide related models of different sizes. Larger models are more capable but also more computationally expensive to run and more expensive to access. Users may choose smaller, weaker models for certain tasks to lower costs.

Panfilov and his colleagues found that feeding encrypted reasoning traces to a smaller version of the same model can reveal the hidden reasoning inside. The smaller models have received less alignment training, meaning that, unlike the bigger ones, they are less likely to refuse to reveal their inner thoughts.