https://openai.com/index/hugging-face-model-evaluation-security-incident/
Seems OpenAI hacked Hugging Face by accident because their model was so focused on solving their eval problems.
I gotta admit I was underestimating the amount of damage a misaligned model could do.
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| We Need To Stop ClosedAI | 0 | 296 | June 23, 2024 | |
| OpenAI hacking model escapes its controlled environment during tests and infiltrates HuggingFace | 1 | 87 | July 22, 2026 | |
| Local AI question | 14 | 1086 | April 18, 2026 | |
| Private online AI (Venice, Duck, etc) | 33 | 6870 | October 5, 2025 | |
| Thoughts on an AI VPN | 15 | 729 | March 27, 2025 |
Massive organizations are monitoring your online activities. Privacy Guides is your central privacy and security resource to protect yourself online.
Privacy Guides is a non-profit, socially motivated website that provides information for protecting your data security and privacy.
We do not make money from recommending certain products, and we do not use affiliate links.