theverge
PublishedSeptember 2, 2026 at 4:40 PM
—neutral
Researchers fear safety disaster ahead of OpenAI’s Astra release

Publisher summary· verbatim
OpenAI is on the cusp of releasing its most powerful AI model yet, Astra, following weeks of delays to shore up safety protocols after its agents attacked real targets during testing. As details about the model trickle out, researchers are warning it "may be the single worst development for AI secur
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from THEVERGE
thevergeOpenAI admits to German wiki ‘incident’5hthevergeRoland is getting into generative AI music with Melody Flip22hthevergeMicrosoft says virtually nobody was grabbing NYT articles through its chatbot1dthevergeRogue OpenAI agents appear to have organized another attack using a German wiki1dThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on theverge ↗