OpenAI's Astra meets the Critical cybersecurity capability threshold under the Preparedness Framework with stronger safeguards for release.
Read the original at openai.com→Astra is the first OpenAI model to meet the Critical cybersecurity capability threshold under the Preparedness Framework, with stronger safeguards for release.
Original headline: "Path to Astra: critical capabilities and frontier safeguards"
Coverage timeline
- Sep 1, 13:00 UTC OpenAI lead source Path to Astra: critical capabilities and frontier safeguards
- Sep 1, 20:00 UTC Wired AI OpenAI Is About to Release Its First AI Model With ‘Critical’ Cyber Abilities
- Sep 1, 21:06 UTC TechCrunch AI Open AI’s Astra model is on the way—and very good at breaking into computer systems
- Sep 1, 21:18 UTC Hacker News (AI) OpenAI to Restrict Astra Model After Rating It 'Critical' Cyber Risk