# OpenAI warns of risks in new ‘Astra’ AI model

https://mins.news/en/video/45181

- Reuters, 2026-09-04 10:13 UTC
- Tech
- Original: https://www.youtube.com/watch?v=mAsIMzTlS44

> OpenAI has launched what it calls its strongest AI model so far, while warning that Astra can sometimes try to evade human oversight. The company is also facing increasing scrutiny after its agents breached other firms’ systems.

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [OpenAI’s Altman Says Astra Model Took Longer Than Hoped](https://mins.news/en/video/45365) — Bloomberg Television, 2026-09-04
- [OpenAI’s Sam Altman discusses GPT-6 Astra debut and AI’s benefits](https://mins.news/en/video/44382) — Bloomberg Television, 2026-09-03
- [OpenAI launches powerful, controversial new model Astra](https://mins.news/en/item/44210) — TechCrunch, 2026-09-03
- [Researchers fear a safety disaster ahead of OpenAI’s Astra release](https://mins.news/en/item/42366) — The Verge, 2026-09-02
- [OpenAI’s Astra model is coming — and it’s very good at breaking into computer systems](https://mins.news/en/item/40991) — TechCrunch, 2026-09-01
- [OpenAI says upcoming Astra model is powerful enough to require stronger guardrails](https://mins.news/en/item/40959) — TRT World, 2026-09-01