OpenAI says its AI agents disabled their own safety monitors
OpenAI has revealed that two of its artificial intelligence agents disabled or weakened systems built to catch them misbehaving, with one later denying it had done so.
22 hours ago
0
16
Security
OpenAI has revealed that two of its artificial intelligence agents disabled or weakened systems built to catch them misbehaving, with one later denying it had done so.
22 hours ago
0
16
Security
Matt Robb wanted to sell his computer keyboard. So he made a listing on Facebook Marketplace—and, as an experiment late last month, he put Meta's new artificial intelligence agent Muse in the driver's seat.
Oct 19, 2026
0
15
Security
Driver-assistance systems are now installed in nearly all modern cars. As a result, safety depends on whether computer systems can reliably process sensor data. Researchers at the Technical University of Munich (TUM) are ...
Oct 8, 2026
0
14
Security
University of British Columbia researchers have uncovered a vulnerability that could allow hackers to target and disrupt critical infrastructure such as water treatment plants and energy grids without needing to break into ...
Oct 15, 2026
0
14
Hi Tech & Innovation
A research team has developed a new biometric authentication technology that can identify users without storing their fingerprint information as digital data. The study is published in Nature Sensors.
Oct 15, 2026
0
14
Internet
People's online behavior has changed in response to legislation to prevent children from viewing harmful content—raising possible privacy and security risks, research suggests.
Oct 16, 2026
0
14
Security
An AI-assisted discovery of vulnerabilities in a widely used programming language led governments and other organizations in Europe and the U.S. to take their websites offline temporarily Wednesday as they scrambled to make ...
23 hours ago
0
14
Security
AI agents don't go rogue. That's something only humans do.
Sep 30, 2026
0
13
Security
Watermarks are increasingly being used to make AI-generated images recognizable and to ensure their origin can be traced. Previous research has focused on whether watermarks can withstand image manipulation. CISPA researcher ...
Oct 9, 2026
0
13
Security
You may recall the scene in the comedy Raising Arizona in which Nicolas Cage pulls a pair of pantyhose over his head before attempting, with limited success, to rob a convenience store of a pack of diapers.
Sep 23, 2026
0
12