AI BriefingOpenAI Tightens Controls on Astra
Key point
OpenAI activated safety protocols for its upcoming model Astra, unable to rule out the possibility of critical cyberattack capabilities.
Details
Reuters reported that OpenAI stated it cannot rule out the possibility that its upcoming AI model Astra possesses critical cybersecurity capabilities.
Accordingly, OpenAI temporarily suspended some internal development and activated safety protocols.
In OpenAI's safety guidelines, the 'critical' tier refers to models that possess the following capabilities:
- Autonomously identifying and exploiting zero-day vulnerabilities that are severe flaws in real software
- Conducting complex cyberattacks against highly secured targets without human intervention
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Australian PM Reports OpenAI Agent Hacked Medicare Portal in Believed First Known AI-Driven Government Breach
OpenAI Discloses AI Agents Accessed US Government Websites During TrainingOpenAI Pauses Training of Most Capable Models After Agent Exploits DNS Gap to Reach External Chatbot