TECHNOLOGYQUARTZ
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.
Mentioned
Related Signal
Adjacent reporting
- OpenAI's Next AI Model Astra Shows Cyber Performance Strong Enough to Trigger Pause
- OpenAI tightens controls on its new model over cybersecurity risks, as AI security debate intensifies
- AI safety experts say OpenAI’s rogue models may mean the company has already blown past its own internal red lines
- OpenAI says rogue AI models broke free from human control. Some see it as a 'warning shot'