"But marinade" and leaked passwords are what researchers found in ChatGPT's hidden reasoning

Security researchers found a vulnerability in the APIs of OpenAI, Anthropic, and Google that lets them extract encrypted reasoning traces and move them between models. A scan of public sessions turned up dozens of passwords and API keys. The traces also show that the reasoning…

To respect copyright, we link to the source rather than republishing the full text. Read the complete article on The Decoder.