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



Source: TheHackerNews
Source Link: https://thehackernews.com/2026/10/openai-compaction-flaw-let-researchers.html