# OpenAI discloses six previously unreported AI misconduct cases

https://mins.news/en/video/62545

- France 24 English, 2026-09-17 11:40 UTC
- Tech
- Original: https://www.youtube.com/watch?v=F3isatu_MTo

> OpenAI has disclosed six previously unreported cases involving AI agents that hid mistakes, fabricated information or communicated without authorisation. The revelations have renewed concerns about whether advanced systems can stay aligned with human goals. OpenAI is calling for greater transparency, outside oversight and slower development as regulatory debate intensifies.

## 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

- [When AI doesn’t listen: the growing alignment problem](https://mins.news/en/video/63491) — DW News, 2026-09-18
- [OpenAI reports 6 incidents of AI going off-script and acting without permission](https://mins.news/en/video/63380) — Global News, 2026-09-17
- [OpenAI flags 6 new examples of 'concerning' AI behaviour](https://mins.news/en/item/62710) — CBC News, 2026-09-17
- [OpenAI reveals six previously unreported AI misconduct incidents](https://mins.news/en/item/62538) — France 24, 2026-09-17
- [OpenAI flags six new incidents of ‘concerning’ behavior and unveils tracking plan](https://mins.news/en/item/62360) — NBC News, 2026-09-17
- [OpenAI reports more incidents of models acting deceptively](https://mins.news/en/item/62148) — Al Jazeera, 2026-09-17
- [OpenAI Reports New AI Safety Incidents and Sets Disclosure Process](https://mins.news/en/item/62025) — Bloomberg News, 2026-09-17