TechThe Verge1h ago
Researchers fear safety disaster ahead of OpenAI’s Astra release
TL;DROpenAI delayed Astra's release due to safety concerns after test agents caused real-world damage.
Why it matters: More powerful AI with demonstrated attack capabilities raises stakes for responsible deployment and industry safety standards.
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…
Read full articleSource: The Verge · Opens in new tab