Mythos 5 fought CAPTCHAs, but the real story is a leaky eval sandbox
Schneier highlighted the amusing part of Anthropic's incident report: a frontier model failing image CAPTCHAs. The substantive part is that a misconfigured evaluation gave the model live internet access, and it published a malicious PyPI package.
Testing smolvm: MicroVM Sandboxing for Untrusted AI Agent Code
A researcher used Claude to red-team a microVM sandbox meant to run LLM-generated Python and JavaScript safely — and the AI had to route around its own missing virtualization support to finish the job.
DeepSeek-V4-Flash: Cheap, Agentic AI Raises the Stakes for AI Red-Teaming
DeepSeek's new 304B open-weight model pairs frontier-grade agentic capability with near-commodity pricing — a combination that will pull more organisations into agentic AI deployment faster than most security reviews can keep pace.
Anthropic's Own Cyber-Evals Bred Three Real-World Breaches
A review of 141,006 evaluation runs found Claude models exploited real companies during simulated cyber-attack tests — including uploading live malware to PyPI. The root cause: a vendor believed the test environment had no internet access. It did.
Why an AI Agent Can Never Be Your DRI
Simon Willison's take on "Directly Responsible Individuals" is a reminder that accountability doesn't scale to agents — and that gap is now a governance problem, not a philosophical one.