OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure

OpenAI says it has broken up a coordinated campaign to copy the hidden reasoning behind its AI models. Researchers found that the same trick kept working for weeks on cloud platforms like Microsoft Azure. In a blog post, OpenAI says it detected and shut down what's known as an "adversarial distillation" campaign. The attackers targeted the models' protected reasoning, meaning the internal steps an AI works through before it gives an answer.

Users typically see only the final result. In distillation, one model learns from another model's full output. That includes the stronger model's complete chains of thought, not just its answers. Those intermediate steps are what make the output so valuable. OpenAI says they can contain information that's deliberately kept out of the final answer, and they can help others recreate a model's capabilities.

According to OpenAI, the activity began at low volume on July 1. On July 24 and 25, it spiked to 16,000 requests from more than 4,000 users, all relying on a typical extraction pattern. A closer look uncovered a network of more than 15,000 accounts…