AIAxios Techabout 2 hours ago
OpenAI expands Astra safety testing over cyber risks
3 min read
OpenAI cannot rule out critical cyber capabilities in its upcoming Astra model, prompting expanded safety testing and paused internal activities that fail stricter security requirements. The move signals rapidly advancing autonomous cyber abilities from AI models.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
Summary by ByteBrief
