AIThe Record1h ago
AI evaluation lab Irregular's report on its role in hacking incidents
AI evaluation lab Irregular's report on its role in hacking incidents involving OpenAI, Anthropic, and Meta models faces criticism over unanswered questions
TL;DRSecurity lab's report on AI hacking incidents leaves key questions unanswered.
Why it matters: Unclear findings undermine trust in AI safety evaluation and incident transparency.
The company at the center of a series of incidents in which AI models compromised real-world computer systems during supposedly …
Read full articleSource: The Record · Opens in new tab