OpenAI shares preliminary cybersecurity evaluations for Astra
OpenAI published preliminary cybersecurity evaluations for Astra, detailing the system's capabilities in critical cyber domains and the security controls it is strengthening in response.
5 sources
Responding to the next frontier of critical cyber capabilitiesopenai.com
After evaluating one of our upcoming models, Astra, we're treating it as our first "critical" model...x.com
OpenAI Pauses Some Work on New Astra Model Over Cyber Concernsbloomberg.com
OpenAI puts the brakes on a new model because it’s supposedly too powerfultheverge.com
OpenAI says it slowed Astra model development over security concernstechcrunch.com
OpenAI by email
Get an email when OpenAI has news
No news that day, no email.
More stories today
- WorkOS argues REST and MCP are complementary, not competing, for agents
- claude-ops turns Claude Code into a business OS with 57 skills, 21 agents
- Tool converts vague feature ideas into specs for Claude Code or Codex
- GitHub Models is now retired
- AI in academic journals: debate overfocuses on today's capabilities