Published Aug 4, 2026, 5:00 PM ET · Updated 3 months ago · 6 sources
Safety testers find more examples of OpenAI, Anthropic models hacking during testing
axios
·
Original Report
INFERY
Two third-party testing firms said Tuesday that they've uncovered more instances where Anthropic and OpenAI's most advanced models tried — and sometimes succeeded in — compromising third-party systems last month.