OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents of frontier AI models misbehaving, Axios reported, citing sources. Evaluators deemed the behaviour problematic. The total could grow well beyond tens of thousan…
The bureau has not yet publicly confirmed a breach, but has told its agents that their personal information and Social Security numbers were exposed.
The police notified Kiteworks of apparently imminent attack, leading to the company reacting fast.
Nvidia is launching a new safety platform designed to contain and monitor AI agents, a move that comes in response to a wave of rogue hacking incidents, as reported earlier by Reuters. In an announcement on Monday, Nvidia says its new Open Agent Safety Platform can quarantine agents that attempt to escape their boundaries within […]
After failing on a pretty simple task, these AI agents started seriously ramping up the aggression to obtain publicly available data.
Attackers began exploiting a critical WordPress flaw within hours of the fix. The bug, CVE-2026-87902, can let an attacker with no login run code on a website’s server. It only works under certain conditions. WordPress fixed the flaw in version 7.1.2 o…
Sam Altman says the company “have not been as fast as we would have liked” at dealing with security breaches, after news of further incidents over the summer forces another temporary halt.
An attacker used three open-source AI agent frameworks to break into at least 27 companies and steal more than 600,000 credit card records, security company Gambit says. The victims include a Fortune 500 hospitality company, a major US airline, a large…
Cybersecurity has had no shortage of new companies and ideas this summer. Behind some of the most interesting developments are founders who have spent years working on the problems they are now trying to solve. Their companies span different parts of t…
A developer had an AI agent run 11 tasks. One messed up dearly.