Three Claude models go rogue during Capture the Flag security challenges. Here's the trail of damage each left behind.

Three Claude models were inadvertently given access to the internet during security evaluations, and each model took a different approach to hacking external systems.

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit ...

You’ve been headhunted for a great job in cryptocurrency. All you have to do is complete a short online assessment – with ...

As AI agents gain autonomy inside enterprises, the biggest cybersecurity threat may no longer be hackers, but the agents ...

System leaks occur when weaknesses are exploited, but what happens when a hacker can leverage clues revealed as part of day to day running?

Britain's AI Security Institute logged 19 rule-breaking actions by OpenAI and Anthropic AI agents in cybersecurity tests.

Filters don't stop prompt injection; architecture does. A field guide to the lethal trifecta, the rule of two, Dual-LLM and ...

Poolside’s Laguna S 2.1 is a new Western open-weight coding AI model that rivals larger systems on benchmarks with transparent evaluation and low-cost deployment.

At 18, cybersecurity student Sami Maghnaoui developed Playback IQ, an AI tool that “replays” soccer matches using raw data.

An artificial intelligence went rogue last week, broke out of its containment before successfully hacking another company, its developer has claimed. According to artificial intelligence developer ...

US President Donald Trump reacts and gestures during a bilateral meeting with India's Prime Minister as part of the G7 summit, in Evian, eastern France, on June 17, 2026. Mandel NGAN/AFP via Getty ...