OpenAI says upcoming model is so capable it requires stronger guardrails
- On Tuesday, OpenAI announced its upcoming model Astra is the first to reach the "Critical" cybersecurity threshold under its Preparedness Framework, marking a significant safety milestone for the company's advanced AI capabilities.
- Astra can identify and exploit unknown software vulnerabilities without human guidance, allowing it to "chain" multiple exploits to penetrate well-protected systems, OpenAI VP of research Amelia Glaese told reporters.
- Following a multi-week pause in training to bolster defenses, OpenAI implemented stronger safeguards including training the model to refuse harmful cyber requests and respect safety restrictions, officials said.
- While OpenAI plans to release Astra "soon," access to advanced capabilities will be restricted using a new "misalignment monitor" that may inadvertently flag legitimate activity as unauthorized behavior.
- Partners in the Daybreak program—including Cisco, Cloudflare, and Palo Alto Networks—will receive early access to a less restricted version to help harden defenses before broader release.
54 Articles
54 Articles
OpenAI announced on the 1st (local time) that it has initiated enhanced security measures for its upcoming next-generation AI model, 'Astra,' after the model reached the 'Critical' level in an internal cybersecurity capability assessment. OpenAI defined the 'Critical' level as the AI model identifying unknown security vulnerabilities (zero-days) in multiple highly secure systems without human intervention and methods to exploit them.
Astra meets the threshold of critical cybersecurity capacity set out in its 'Preparation Framework'.
OpenAI announced that its next-generation AI model, 'Astra,' has reached the 'critical' level for the first time in its internal cybersecurity capability assessment. The company plans to launch Astra soon with restricted access to advanced cybersecurity capabilities. OpenAI 1
"Astra is able to detect more security gaps than previous models. It is the first time that a model triggers the most stringent, so far only theoretical security requirements of OpenAI.
OpenAI is preparing an Astra, the first model of a company that has reached the critical threshold of cybersecurity and has been able to detect two self-identifiers of the "zero-day" type.
Coverage Details
Bias Distribution
- 50% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
