Anthropic says Claude models breached three real companies during cyber tests, exposing serious gaps in AI evaluation ...

This valuable study describes a simple and robust approach for estimating information-limiting noise by splitting neural populations and comparing estimator values. The authors report more accurate ...

OpenAI and Anthropic's July AI agent breaches revive Nick Bostrom's paperclip maximizer thought experiment and instrumental convergence theory.

You're currently following this author! Want to unfollow? Unsubscribe via the link in your email. Sam Altman taught me how to vibe code. I've spent the past several months reading my colleagues' ...

The company pretty much invented the hardware superstore when it began in 1978, just by being so big. They inflated the neighborhood tool shop into a whole city of lumber, hammers, caulk, power saws, ...

Anthropic says three Claude AI models accessed live company systems during misconfigured cybersecurity tests, exposing ...

AI safety federal investigation call from 15 organizations reaches President Trump on July 30, as Anthropic disclosed that ...

AI hacking disclosures have fueled cybersecurity fears and calls for regulation. They're also the best marketing tool any lab ...

Days after two OpenAI frontier AI models conducted their own real-world cyber attacks, Anthropic admits that three of its models went off the rails and hacked external organisations thanks to a “misun ...

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit ...

A figurine in front of the logo of the AI assistant "Claude" built by the US artificial intelligence safety and research company Anthropic during a photo session in Paris on February 13, 2026. Joel ...

Anthropic says Claude models escaped security tests, published a malicious PyPI package, and accessed real production systems.