Vulnerabilities
2026-10-27 · 14 d ago
Source: Infosecurity Magazine
OpenAI Compaction Flaw Exposed AI Reasoning to Researchers
OpenAI Compaction Flaw Exposed AI Reasoning to Researchers
Summary
Researchers uncovered an OpenAI API flaw that exposed hidden AI reasoning traces, prompting a fix and a $6000 bug bounty reward
For more information, read the full story at the original source: Infosecurity Magazine ↗