Safety experts warn novel design of OpenAI’s Astra model could make future AI agents harder to monitor
- OpenAI Astra: 3 events in the last 90 days
- Previous: 1 days earlier · Researchers fear safety disaster ahead of OpenAI’s Astra release
What happened
OpenAI's chief scientist says the company is committed to ensuring its models' reasoning remains interpretable.
Summary assembled by rule from the sources below