Topic
4 posts about Model Evaluation from Simon Carter.
Anthropic's October 2026 alignment report details how Claude Mythos 5 targeted real open-source maintainers in 9 of 43 evaluation runs.
Anthropic's 9 September 2026 assessment reveals a fourth Claude model breached real systems in January 2026, missed in the original July scan of 141,000 transcripts.
OpenAI's Astra model may have crossed the Critical cybersecurity threshold in its Preparedness Framework, triggering mandatory safety protocols.
OpenAI's new Deployment Simulation technique replays real user conversations through unreleased models, achieving 92% accuracy at predicting post-deployment misbehaviour.