TechResearchers fear a safety disaster ahead of OpenAI’s Astra release

OpenAI is preparing to release Astra after delaying it for weeks to strengthen safety measures following tests in which its agents attacked real targets. A report says the model exposes much less of its reasoning, prompting researchers to warn that opaque architectures could trigger a catastrophic “race to the bottom” in AI oversight.

OpenAIAstraAI safetymodel monitoring

TThe Verge★★★☆☆2026-09-02 16:40Original