
OpenAI calls Astra its most dangerous model yet - watching what it does is only getting harder
A frontier lab is shipping a model with acknowledged dangerous capabilities while simultaneously acknowledging its safety instrumentation (chain-of-thought monitoring) cannot reliably observe what the model is actually doing. This is a live debate about interpretability, capability, and risk management at the frontier.
Why it ranks · · Astra rated as first OpenAI system with 'critical' cyber capabilities · 2026-09-02
Read full story