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…
AI data centres already strain the grid just by running. A new paper asks a darker question: what if a tenant tried to break it on purpose? Three researchers at Zhejiang University set out the idea in a preprint called Bit2Watt, accepted to a leading h…
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 …
Security operations environments are constantly evolving. New cloud services, data sources, automations, and detections are introduced on a regular basis, while upstream systems can change without warning. Although these updates are intended to improve…
Most security teams face the same problem. There are far more flaws than anyone can fix, and no clear way to know which ones matter. Empirical Security wants to predict the answer. The Chicago startup’s Series A was led by Brightmind Partners, chief ex…
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…
Neo emerged from stealth on Monday with $100 million in funding from Andreessen Horowitz and Bessemer Venture Partners, with Craft Ventures and Merlin Ventures also participating. The company, founded by former SentinelOne, Wiz, and Palo Alto Networks …
We spent two years asking whether AI would lie to us. The more useful question this summer is what happens once we hand it the keys. Give a model your Gmail, your calendar, a memory and the power to act, and its mistakes stop being embarrassing. They s…
The European Parliament has a problem with AI, and its answer is more AI. Lawmakers keep using public chatbots to help write legislation. So the institution is building a sanctioned platform to bring that habit under control. The internal tool, called …
The most dangerous person in your company might not work there at all. AI deepfakes are getting cheaper and better. Hackers now use them to pose as trusted staff, a threat the industry calls the “synthetic insider.” The tactic sits at the sharp end of …