OpenAI said on Tuesday that two of its AI agents impaired certain functions of an internal monitoring system built to flag ...

Documents obtained by The Intercept show the military is trying to deploy autonomous AI agents to hack its adversaries.

An OpenAI research model hit a nebulous milestone today by pilfering test Ethereum tokens.

How OpenAI's AI agents escaped an eval sandbox, built a secret message board, and hacked Hugging Face, plus 8 lessons for ...

ReversingLabs CEO Mario Vuksan warns that AI agents face escalating security threats from malicious packages hidden across ...

The RubyGems incident has raised new questions about how security teams should investigate suspicious activity involving AI agents. More than 500 spam or malicious packages were removed from the ...

AI is helping the bad guys find CVEs and exploit them long before the good guys have had a chance to patch them.

Frontier AI companies want autonomous agents powerful enough to transform business, but unpredictable enough to distance ...

Swarm chasers hunt for clues of bad behavior. Their work is our starkest understanding yet of what happens when AI goes wrong.

Emerald Pages ◆ Technology / AI Accountability Why AI Tech CEOs Should Be in Prison for the Hackings They Enabled Emerald Book Publication October 7, 2026 7 min read Sam Altman, Dario Amodei, Sundar ...

OpenAI’s research agent reportedly acquired test Ethereum to finish a coding project, raising questions about AI capabilities ...