Safety overview: GPT-6 Astra
Source: OpenAI
Intel Summary
OpenAI has published a safety overview for GPT-6 Astra, identifying it as its most capable broadly deployed model. According to OpenAI, GPT-6 Astra is its first system to reach the Critical tier for cybersecurity capabilities evaluated under the company's internal Preparedness Framework.
Why It Matters
Reaching a critical tier under a frontier safety framework highlights growing offensive and defensive cyber capabilities in advanced models. The evaluation indicates heightened dual-use risk, necessitating targeted safety mitigations, heightened monitoring, and enhanced governance protocols for enterprise and security teams managing autonomous or frontier AI deployments.
Part of an ongoing development
Developing storyPrimary sourceOpenAI reports Astra model crosses Critical cybersecurity capability threshold
OpenAI says its upcoming Astra AI model is its first to reach a "Critical" cybersecurity capability threshold, according to CNBC. The company stated that Astra will be released soon, though access to its cybersecurity capabilities will be restricted. Claims are as reported; this summary makes no determination about accuracy or significance.
- Confidence
- Very high confidence
- Corroboration
- Widely corroborated
More coverage of this development
- Open AI’s Astra model is on the way — and very good at breaking into computer systemsTechCrunchIndependent reporting
- OpenAI says Astra AI model is its first that crosses 'Critical' cybersecurity capabilityCNBC TechIndependent reporting
- OpenAI Is About to Release Its First AI Model With ‘Critical’ Cyber AbilitiesWIREDIndependent reporting
Organizations & Entities
Topics
Related Intelligence
- ReportSame development
OpenAI Is About to Release Its First AI Model With ‘Critical’ Cyber Abilities
OpenAI plans to release "Astra," an AI model featuring critical cyber capabilities, according to WIRED. The company is providing early access to select partners to allow them time to reinforce defensive security controls prior to broader availability.
WIRED - ReportSame development
Open AI’s Astra model is on the way — and very good at breaking into computer systems
OpenAI is preparing to release Astra, a new large language model possessing advanced capabilities for penetrating computer systems. Ahead of the launch, the company previewed safety precautions and risk mitigation measures designed for the cyber-critical model.
TechCrunch - ReportSame development
OpenAI says Astra AI model is its first that crosses 'Critical' cybersecurity capability
OpenAI says its upcoming Astra AI model is its first to reach a "Critical" cybersecurity capability threshold, according to CNBC. The company stated that Astra will be released soon, though access to its cybersecurity capabilities will be restricted.
CNBC Tech - DevelopmentDevelopingAlso involving OpenAI
OpenAI launches Astra model
TechCrunch reports that OpenAI has launched Astra, a new model designed for computer and browser use. Claims are as reported; this summary makes no determination about accuracy or significance.
7 independent sources