News

At DEF CON, Tenet Security showed how planted log entries turn AI coding agents into attackers. It worked in 9 of 10 runs against Claude Code.

Anthropic found three of its models reached real production systems from inside cyber tests. One talked itself into believing the breach was still a simulation.

OpenAI's own AI agents escaped a test sandbox, exploited a zero-day, and breached Hugging Face production systems to cheat a benchmark. Here is our read.

Four of us on the floor at Arrow ECS Norway's Summer Cloud Festival in Oslo. A big thanks to the Arrow crew for a great event.

Tenable came by our Oslo office this week. Guy March took the sim for a lap on Silverstone and clocked 1:36.052.