Irregular Says ‘Human Oversight’ Responsible for AI Sandbox Escape Incidents

Irregular says ‘human oversight’ responsible for AI sandbox escape incidents

A company that runs AI testing labs involved in a series of breaches carried out by Anthropic and OpenAI’s cyber-focused models said the incident happened in part because they “unintentionally” provided the models with access to the internet. In a blog posted Friday, Irregular said it partners with frontier labs to “stress test” AI models for security risks before they’re deployed, including simulations of their vulnerability research capabiliti…

OpenAI president says companies should do 10 things ASAP to defend against AI cyber threats

OpenAI President Greg BrockmanSteve Marcus/ReutersGreg Brockman warned that "time is of the essence" for companies upgrading their cybersecurity.The OpenAI president said AI-powered attackers will soon be able to exploit vulnerabilities.Brockman said that, at the same time, AI tools can help companies identify what they need to fix.OpenAI's president is ringing the cybersecurity alarm bell.Greg Brockman says companies need to act now to secure t…

AI Agents Gain Unintended Internet Access During Cybersecurity Evaluations

AI security evaluation firm has disclosed that several frontier AI models unintentionally accessed and acted against real internet-connected systems during controlled cybersecurity testing. This issue, which has since been resolved, stemmed from a single evaluation scenario in which internet access was permitted and a fictional target name overlapped with a real domain. Irregular stated that […] This article has been indexed from GBHackers Secur…

After OpenAI and Anthropic, now Meta's AI model hacks another company during testing

In a fresh headache for Meta CEO Mark Zuckerberg, one of the social media conglomerate’s AI models, in the first week of August 2026, ended up hacking another company during cybersecurity testing, fanning concerns about how developers can contain increasingly capable AI systems after similar recorded incidents ‌at rivals Anthropic and OpenAI. The incidents at Meta and Anthropic had one thing similar: configuration errors inadvertently giving awa…

AI Rogue Strikes: Independent Agent Triggers Massive Cyber Attack

NewsFinale NewsFinale Journal This story was first shared on Modernity and is reprinted here with permission. Special contribution by @ModernityNews The most advanced AI creations from OpenAI have broken away from expected norms. Amid a security evaluation, one of OpenAI’s digital agents managed to escape its confines, exploited a previously unknown vulnerability, secured unfettered internet access, and proceeded […] The post AI Rogue Strikes: I…