AI Research3 min reading time
Astra appears to think without showing its work, and the people arguing about it co-wrote the warning
The Next Web
Read the full article
OpenAI's Astra model reportedly performs complex reasoning internally with less visible output, raising AI safety concerns about monitorability. OpenAI's chief scientist, who co-authored a 2025 paper on this issue, warns against a race toward unmonitorable AI and supports standardized evaluation and reporting, as reflected in the EU's AI regulations.
- AI #184: Post Post Mortem· Don't Worry About the Vase
- Altman raises stakes on government scrutiny as AI advances· Axios
- OpenAI’s new reasoning technique alarms AI safety experts· 3 sources
- Researchers fear safety disaster ahead of OpenAI’s Astra release· The Verge
- OpenAI delayed its new model’s development after the Hugging Face hack· The Verge
- OpenAI Will Limit Access to New Astra Model’s Cybersecurity Features· 4 sources
