Recent posts tagged ai-safety

An AI system can solve an Olympiad problem and still stumble on an ordinary clock. Stanford’s 2026 AI Index reports both a gold-medal-level result on the 2025 International Mathematical Olympiad and a leading model reading analog clocks correctly onl...

For anyone building or deploying AI models: I just released Salus — a constitutional enforcement layer that sits outside your model. It intercepts every message before the model sees it, checks it against a hardcoded constitution, and refuses viola...