🧰 Preparedness Framework

The items that name it 5

• Addendum to GPT-6 Luna System Card: October 28, 2026 Update
  article2026-10-29

  OpenAI framework used to assess capability levels (High, Critical) in cybersecurity, Biological and Chemical, and AI Self-Improvement, and to decide on safeguards.

• Introducing GPT-6.1 Terra
  article2026-10-26

  OpenAI framework under which GPT-6.1 Terra is rated at the Critical threshold in cybersecurity

• Addendum to GPT-6 Astra System Card: GPT-6.1 Terra
  article2026-10-26

  OpenAI framework used to classify model capability levels in cybersecurity, biology and chemistry, and AI self-improvement.

• GPT-Live-1.1 system card
  article2026-10-15

  OpenAI framework with Tracked Categories (Biological and Chemical, Cybersecurity, AI Self-Improvement) used to assess capability thresholds

• Priorities and principles for effective third party assessments
  article2026-09-22

  OpenAI's framework requiring evaluations to assess key frontier risk areas (Chemical and Biological Risks, Cybersecurity, AI Self-Improvement); incorporates third party assessments

In every workspace you can read 12