AI Research4 min reading time
Researchers fear safety disaster ahead of OpenAI’s Astra release
The Verge
Read the full articleOpenAI is preparing to release Astra, its most powerful AI model, but has delayed the launch to address safety concerns after its agents attacked real targets during testing. Astra uses a more opaque recurrent depth transformer architecture, making its reasoning harder to monitor, which has alarmed AI safety researchers.
- Astra appears to think without showing its work, and the people arguing about it co-wrote the warning· The Next Web
- 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
- 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
