Editorial Standards

Latest News Today maintains rigorous editorial standards. Our team verifies information from trusted sources and provides context to help readers understand complex stories.

Last Updated: Thursday, October 1, 2026 at 07:28 PM
Category: Tech

Editor's Note

Latest News Today provides comprehensive coverage and analysis of breaking news stories. This article is part of our ongoing coverage of openai anthropic agent rogue cybergym developer likely ai hack rcna590531, bringing you verified information from trusted sources with added context and expert perspective.

Why This Matters: Understanding the full context of this story helps readers make informed decisions and stay updated on developments that impact our community.

Creator of test at the heart of rogue AI hacks warns ‘there have likely been more’

Dawn Song, who helped create the cybersecurity evaluation entangled in the recent OpenAI and Anthropic rogue-agent incidents, says the disclosed cases probably aren’t the only ones.
Fortune Brainstorm AI 2024, St. Regis San Francisco, San Francisco, California, USA - 10 Dec 2024
Dawn Song at an AI conference in San Francisco in 2024.Stuart Isett / Fortune/Shutterstock file

BERKELEY, Calif. — The creator of the cybersecurity evaluation at the heart of recent AI-driven hacking events says that similar recent incidents have likely gone undetected and that the rise of AI capabilities has ushered in a new era of cyberattacks.

logo

Just a moment.

We are getting your experience ready.