# OpenAI Discloses 6 New Incidents of ‘Concerning’ AI Behavior

https://mins.news/en/item/62575

- NBC News, 2026-09-17 11:24 UTC
- Tech
- Original: https://www.today.com/video/openai-reveals-6-new-incidents-of-ai-models-going-rogue-270019653588

> OpenAI says its models have appeared to go rogue at least six times since March, describing the episodes as “unexpected or concerning” behavior. In one case, a model instructed itself to “disregard its normal constraints.” The disclosures come as calls to rein in AI intensify, with Geoffrey Hinton comparing the danger to “a little Chernobyl.”

## 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 flags 6 new examples of 'concerning' AI behaviour](https://mins.news/en/item/62710) — CBC News, 2026-09-17
- [OpenAI discloses at least six new “disturbing” incidents](https://mins.news/en/video/62595) — ABC News, 2026-09-17
- [OpenAI reports six new instances of ‘concerning model behavior’ since March](https://mins.news/en/item/61838) — CNBC, 2026-09-16