Protesters congregated at a Portsmouth hotel after false rumours that a coach of migrants had arrived.

You can no longer assume a mere VM will contain a sufficiently advanced AI agent.

It won't work: My suspicion was that GPT 5.6-Cyber would succeed, but the frequency and manner of its success removed all doubt. We have to reassess sandboxing quality for capable AI agents, and in general the software stack with which they interact. An off-the-shelf VM is not enough to contain a modern, cyber-capable AI agent. There is simply too much attack surface. Even innocuous features (like running with a display) add extra, exploitable attack surface.

OpenAI gave a last-minute presentation at the Black Hat security on Wednesday about “the Hugging Face Incident” (previously on this blog). The video was published yesterday. It’s short and information...

During a routine cyber evaluation, AISI identified an incident in which AI agents took sustained, unsanctioned action directed at real people and organisations. We are disclosing what we found, what i...

We’ve been covering Australia’s monumentally stupid social media ban for kids under 16 since before it went into effect. We noted how dumb the whole premise was, how the rollout was an …