16th March 2026
The point of the blackmail exercise was to have something to describe to policymakers—results that are visceral enough to land with people, and make misalignment risk actually salient in practice for people who had never thought about it before.
— A member of Anthropic’s alignment-science team, as told to Gideon Lewis-Kraus
Recent articles
- Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7 - 16th April 2026
- Meta's new model is Muse Spark, and meta.ai chat has some interesting tools - 8th April 2026
- Anthropic's Project Glasswing - restricting Claude Mythos to security researchers - sounds necessary to me - 7th April 2026