… After gaining access to the internet, it then exploited a security vulnerability in a third-party service, "in a matter similar to previously reported instances with other companies." It was also due to a misconfiguration by Irregular that Anthropic's models were able to leave their testing environ… …
The ChatGPT desktop app for Mac just got hit with a security breach By Lawrence Bonk May 14, 2026 1:20 pm EST OpenAI's ChatGPT app for Mac just experienced a security breach involving two employee devices, according to a report by 9to5Mac . …
… Find and fix vulnerabilities earlier with Daybreak pic.twitter.com/yobOSWYeWP — OpenAI @OpenAI May 11, 2026 Daybreak will use GPT-5.5 for general purposes and GPT-5.5 with Trusted Access for Cyber for most defensive security workflows, including "secure code review, vulnerability triage, malware an…
… Meanwhile, Daybreak Red provides partners access to cybersecurity models that were especially trained for vulnerability research, security resting and exploit validation. …
… According to US cybersecurity startup Frontier , Kimi K3 broke out of a sandbox from the UK government's AI Security Institute AISI while its defensive cybersecurity skills were being evaluated. …
… The models didn't exploit vulnerabilities to access the internet this time, but they did act beyond the scope of their testing parameters. To be particular, the incidents took place during a single test that challenged AI agents to solve a cyber security problem. …
… Building the scaffolding that gives people a way to access parts of that platform from their mobile device seems like a no-brainer. …
… In the middle of testing, they became hyperfocused on solving an evaluation problem, going to great lengths to find internet access in order to find a solution for it. …
… To activate it, open ChatGPT's settings menu and select Safety and security . Under Advanced security , tap Lockdown mode and flip on the toggle. …
… 10, 2026 5:19 am EST Shortly after a major cybersecurity incident where OpenAI's models hacked into an open source machine learning platform called Hugging Face , the company announced that it's bolstering safeguards and security controls for its latest AI model. …