I extracted the safety filters from Apple Intelligence models

I managed to reverse engineer the encryption (refered to as “Obfuscation” in the framework) responsible for managing the safety filters of Apple Intelligence models. I have extracted them into a repository. I encourage you to take a look around.


Comments URL: https://news.ycombinator.com/item?id=44483485

Points: 122

# Comments: 38

https://github.com/BlueFalconHD/apple_generative_model_safety_decrypted

Établi 1mo | 6 juil. 2025, 21:50:11


Connectez-vous pour ajouter un commentaire

Autres messages de ce groupe

Show HN: OWhisper – Ollama for realtime speech-to-text

Hello everyone. This is Yujong from the Hyprnote team (https://github.com/fastrepl/hyprnote).

We built OWhisper for 2 reasons: (

14 août 2025, 20:20:18 | Hacker news
Show HN: Modelence – Supabase for MongoDB

Hi all, Aram and Eduard here - authors of Modelence (https://github.com/modelence/modelence), an all-in-one backend platform for

14 août 2025, 20:20:15 | Hacker news