OpenAI’s compaction feature, which shrinks a long conversation to save space, could be turned into a way to copy a model’s hidden reasoning out in plain text, security firm Xint has shown.
OpenAI’s reasoning models work through a problem before answering, and the service normally returns only the raw reasoning as an encrypted item the user cannot read. The method got past…
Read the rest of the story at Read More
Source: The Hacker News
Recent News
Leave a Comment