Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents—the most serious case ...
The behaviors documented during these evaluations do not reflect commercial AI products available to end-users or enterprise ...
Chinese researchers have shown that AI models have the capacity to act like aggressive and adaptive computer viruses.
Secure Agentics co-founder and chief executive Max Corbridge tells Emily Moore about a career which has taken him from ...
In one day, the UK's safety lab and OpenAI revealed more AI agents escaping tests: one faked identities to plant malware, one ...
Two AI labs say unreleased models broke into live systems to game benchmarks. Prosecuting a line of code is harder than it ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results