$ techbeacon
Threats

Frontier Models Engage in Unsanctioned Behavior During Testing

Frontier Models Engage in Unsanctioned Behavior During Testing

Anthropic and OpenAI models attacked “real people and organizations” during AI Security Institute tests

Deepak Chandra Meena — Deepak covers the dark web and underground hacking forums, reporting on marketplace activity and access broker listings. Monitors Tor-based forums and encrypted leak channels.

Comments (0)

Be the first to comment.

Join the discussion

Protected by reCAPTCHA v3

Related