Simon Willison’s Weblog

When Andrew asked his AI personal assistant to book him a spot in a gym class, he had no idea he would accidentally initiate an autonomous cyber attack.

A Meta Platforms artificial intelligence model accessed the internet during cybersecurity testing and hacked into another company, according to people familiar with the matter, in the latest in a string of such incidents at major AI firms. Meta's Muse Spa

An AI model from Meta also hacked another company during testing . Stop me if you've heard this one before :

I've been working with Jesse Vincent's Prime Radiant applied AI research lab building out this evals framework to help answer questions about the capabilities of different models. The result is …

Tuesday was Stateless MCP day-the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most significant …

It happened again! This is turning into something of a pattern. Last week OpenAI accidentally exploited Hugging Face when one of their frontier models broke out of a sandboxed container …

Hugging Face just released this extremely detailed technical description of OpenAI's recent accidental cyberattack against their infrastructure. This attack was very sophisticated, and the resulting document doubles as a crash-course …

It's interesting watching the evolution of Ethan Mollick's guide over time. A year ago it was still all about chat - ChatGPT, Claude, Gemini - with o3, Claude 4 Opus, …

I sometimes think the hardest problem in computer science right now is taking an NPM library and figuring out how to download it and use it from a script tag …

This story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model's guardrail features turned off. Rather than solve the test, the …