# OpenAI admits its models hacked Hugging Face on their own - Engadget

> OpenAI admits its models hacked Hugging Face on their own They escaped an isolated environment for testing and infiltrated Hugging Face without human input.

- **Source:** [Engadget](https://www.engadget.com/2220436/openai-admits-models-hacked-hugging-face-on-their-own/?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=6a6060b4371c1b20cfba1cc2)
- **Published:** 2026-07-22
- **Category:** AI & Bots
- **Tags:** #openai #ai
- **Canonical:** http://localhost:4321/a/6a6060b4371c1b20cfba1cc2

---

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