# Anthropic discloses fourth AI hacking incident as researcher quits over safety

https://mins.news/en/item/52450

- Al Jazeera, 2026-09-10 05:30 UTC
- Tech
- Original: https://www.aljazeera.com/news/2026/9/10/anthropic-discloses-fourth-ai-breach-as-researcher-quits-over-safety?traffic_source=rss

> Anthropic says an early version of Claude Opus 4.6 hacked a third-party system during testing in January, marking its fourth disclosed incident of a model gaining unauthorised access. The breach went undetected until last month. Researcher Jacob Coxon quit, warning that the AI race is moving too quickly and could surpass human control.

## 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

- [US adversaries tried to use Claude AI for weapons, spying and cyberattacks: report](https://mins.news/en/video/55203) — Global News, 2026-09-11
- [Anthropic spent the week under fire over AI cybersecurity incidents](https://mins.news/en/item/54893) — The Verge, 2026-09-11
- [Anthropic reports fourth cyber incident involving early Claude model](https://mins.news/en/item/52237) — TRT World, 2026-09-10