OpenAI stalls Astra model after it hit a ‘critical’ cyber threat level
Internal tests showed Astra can craft functional zero‑day exploits without human input, crossing OpenAI’s ‘critical’ cybersecurity threshold. That prompted a pause and tighter isolation, meaning the model’s public rollout is delayed and access may be restricted to vetted security teams. The move underscores how advanced AI agents can become a direct cyber‑risk.