←back to thread

I extracted the safety filters from Apple Intelligence models

(github.com)
534 points BlueFalconHD | 1 comments | 06 Jul 25 19:50 UTC | HN request time: 0.207s | source

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.
1. RachelF ◴[07 Jul 25 07:22 UTC] No.44487576[source]▶
In the 1970's George Carlin had "7 Words You Can't Say On TV" and got into legal trouble for saying them during his live skits.

Seems like Apple now has a list of 7,000 words you can't use on an iPhone now.