general
Imported story
OpenAI Compaction Flaw Let Researchers Bypass Hidden Reasoning Protections
Source: The Hacker News · Published · Last checked 13 minutes ago · 1 min read
Read original source ↗ (thehackernews.com)
Publisher excerpt From The Hacker News
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
Excerpt only, shown with attribution. This content belongs to the original publisher and has not been independently verified by CyberSecurity.pk.