# Anthropic sees OpenAI cybersecurity disaster and says 'hold my beer,' reveals it accidentally hacked 3 companies in as many months without noticing

> First reported by Wired, AI company Anthropic revealed in a July 30 blog post that its AI agents escaped testing environments on three separate occasions since April, accessing the internet and successfully hacking…

- **Source:** [Pcgamer](https://www.pcgamer.com/software/ai/anthropic-sees-openai-cybersecurity-disaster-and-says-hold-my-beer-reveals-it-accidentally-hacked-3-companies-in-as-many-months-without-noticing/?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=6a6d11c1e4f45170661d146f)
- **Published:** 2026-07-31
- **Category:** Gaming
- **Tags:** #openai #anthropic #ai
- **Canonical:** http://localhost:4321/a/6a6d11c1e4f45170661d146f

---

_GearOpen's distilled summary. The full original article is published at Pcgamer (source link above); GearOpen does not republish the source's full text._