OpenAI Classifies Astra As Its First Critical Cybersecurity Risk Model
0:00 / 0:49
News
OpenAI Classifies Astra As Its First Critical Cybersecurity Risk Model
calendar_today Date:
schedule Duration: 0:49
database
Summary Report
OpenAI's Astra is the first model to reach the critical threshold for cybersecurity risk under its Preparedness Framework, and OpenAI is slowing its development to add safeguards.
- 01. OpenAI is isolating Astra's test environments, restricting network and tool access, hardening weight storage, and monitoring every agentic run
- 02. It's the first time any lab has actually triggered its own critical-risk threshold rather than just planning for the possibility
OpenAI has classified its upcoming model, Astra, as the first model ever to reach the critical threshold for cybersecurity risk under its Preparedness Framework. Internal evaluations showed Astra making significant advances in agentic coding and cybersecurity, so OpenAI is slowing its development and adding safeguards.
