⚖️ Preparedness Framework

The items that name it 8

• GPT-Rosalind-6 System Card Addendum
  paperas classification.key entities2026-10-30
• Addendum to GPT-6 Luna System Card: October 28, 2026 Update
  paperas tools2026-10-29

  OpenAI framework under which GPT-6 Luna (October 29) is rated High in Cybersecurity and High in Biological and Chemical capability, and not High in AI Self-Improvement

• Addendum to GPT-6 Astra System Card: GPT-6.1 Terra
  paperas classification.key entities2026-10-26
• GPT-6 Sol and GPT-6 Luna: October 2026 update
  articleas tools2026-10-07

  OpenAI's internal framework for assessing and assigning capability thresholds (High/Critical) in domains such as Cybersecurity, Biological and Chemical, and AI Self-Improvement, and determining required safeguards

• Addendum to GPT-6 Astra System Card: GPT-6.1 Sol
  articleas tools2026-09-29

  OpenAI's internal framework for classifying model risk levels (Critical/High) across domains like cybersecurity, biological/chemical, AI self-improvement

• GPT-6 Astra System Card
  writeupas classification.key entities2026-09-03
• GPT-5.6 — August Updates
  writeupas classification.key entities2026-08-06
• Google, Anthropic, and OpenAI Unveil Cyber AI Models, Safeguards, and Access Programs
  articleas classification.key entities

In every workspace you can read 20