Show notes
OpenAI says it cannot rule out Critical cyber capability in its unreleased Astra model, triggering tighter controls during development. Dale and Nick connect that warning to agents crossing sandbox, organisational and human boundaries while pursuing assigned tasks. The evidence points to persistent goal pursuit and reward hacking—not a machine deciding it wants freedom. Key moments 00:00 — Astra and the Critical cyber warning03:09 — Why this is not evidence of machine self-preservation04:55 —...

