OpenAI says it slowed Astra model development over security concerns

OpenAI suspended parts of its Astra model development after an internal review found it had reached a 'critical cybersecurity threshold'—able to independently identify and carry out attacks on well-protected real-world systems. The company disclosed the decision in a blog post, but the article doesn't give a timeline for resuming work.

Why it matters: OpenAI disclosed it paused Astra development after the model autonomously found and exploited real-world system vulnerabilities. This is the first time a major lab has publicly halted an internal project on security grounds. The lack of a timeline adds weight. Downside: the bl...