OpenAI says its AI models mistakenly breached open-source AI platform Hugging Face during internal testing. In a blog post on Tuesday, OpenAI writes that GPT-5.6 Sol and “an even more capable pre-release model” discovered vulnerabilities within their sandboxed testing environment, allowing them to gain access to the internet and target Hugging Face. On July 16th, […]
OpenAI said on Tuesday that two of its AI models, including the flagship Sol, broke out of a secure test environment, gained internet access by exploiting a zero-day vulnerability in third-party software, and hacked into Hugging Face’s production infra…
OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing gone awry.
The tools are Cursor, OpenAI’s Codex, Google’s Gemini CLI, and Antigravity. Over several months, Pillar Security found ways for each agent to cross its security boundary while staying, technically, inside the box. The escape that isn’t one The trick is…
OpenAI says the agentic side of ChatGPT has passed 10 million weekly users, a mark it reached less than two weeks after the debut of ChatGPT Work, its attempt to turn the chatbot into a tool that finishes a job rather than just describes one. The figur…
ChatGPT is a reassuring and knowledgeable money coach, but does that mean we should let our guard down?
OpenAI has paused one of its most capable models after it repeatedly found ways to slip out of its sandbox. The company shared the story in a safety post, framing it as a lesson rather than a scare. This is not just any system. About two months ago it …
If you run a WordPress site, the advice this week is blunt: update it now. Two flaws in the software are under active exploitation across the internet. WordPress powers more than half of every website online, so the blast radius is huge. Security firms…
On Sunday evening, as Spain and Argentina played out the World Cup final, the mathematician Levent Alpöge posted a short message on X. The Jacobian conjecture, he wrote, is false. He thanked a friend for asking about it, and another friend, “fable,” fo…
ChatGPT’s new Work mode is designed for business tasks, but you can also use it for your daily admin.