Dossier
safety framework
Coverage of safety framework in the Nexus archive.
- OpenAI paused work on its Astra model after it warned the AI might be capable of autonomous cyberattacks
OpenAI has paused its work on the Astra model after receiving warnings regarding its potential capability for autonomous cyberattacks. This decision was made following preliminary evaluations which found the unreleased model had reached a "critical" cybersecurity threshold under the company's internal safety framework.