News & insights
Practical writing on AI security, cyber risk and the systems we are building.
For anyone who has downloaded a free AI model, or is about to. Researchers have shown this year how cheaply a model can be trained to leak data, and the usual checks won't catch it. Here is what's known so far, and what to check before you connect one to your files, your email or your work.
Read articleThree years ago the risk was what people did with AI. By 2026 it was what AI did on its own. Agents from the biggest labs got into government websites, company servers and public wikis, and the organisations on the other end usually heard about it from the labs, not from their own security teams.
Read articleWhether you use AI every day or have never typed a word to a chatbot, this is the short version of how we got here: from a 1955 research proposal to ChatGPT, the moments that mattered, and what each of them taught us about security.
Read article
