# AI models from Anthropic and OpenAI were caught breaking the rules again

> OpenAI and Anthropic have both had a rough few weeks on the AI safety front. OpenAI recently disclosed that its models broke out of a test environment and hacked into Hugging Face and four other organizations.

- **Source:** [Digital Trends](https://www.digitaltrends.com/computing/ai-models-from-anthropic-and-openai-were-caught-breaking-the-rules-again/?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=6a72d5def65b9cf9869421f4)
- **Published:** 2026-08-05
- **Category:** AI & Bots
- **Tags:** #openai #claude #anthropic #ai
- **Canonical:** http://localhost:4321/a/6a72d5def65b9cf9869421f4

---

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