OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face | Dark Hacker News

Dark Hacker News

new|best|ask|show|jobs

Built with the HackerNews API. Developed by LJT.AI

Note: The HackerNews API provides up to 500 stories per category

OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face(thenextweb.com)

2 points by hsuduebc2 27 days ago | 3 comments

OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face | Dark Hacker News

ChrisArchitect 27 days ago |

[dupe] https://news.ycombinator.com/item?id=48997548

hsuduebc2 27 days ago |

It seems that it all is going in the way everybody expected.

therealpygon 27 days ago |

“OpenAI confirms their agent harness and security failures allowed a prompted AI to exceed permissions.” Would be a more descriptive title without OpenAI FUD.