AIThe New Stackabout 2 hours ago
OpenAI Astra hits Critical cybersecurity threshold
4 min read
OpenAI's Astra model is the first to reach the Critical threshold in its Preparedness Framework, meaning it can find vulnerabilities and develop exploits with less human help. Astra will face closer monitoring that can interrupt agents mid-task; ChatGPT and Codex users may review paused actions, while API jobs simply stop.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
Summary by ByteBrief
