←back to thread

I extracted the safety filters from Apple Intelligence models

(github.com)
534 points BlueFalconHD | 2 comments | 06 Jul 25 19:50 UTC | HN request time: 0.436s | 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. neuroticnews25 ◴[07 Jul 25 12:27 UTC] No.44489657[source]▶
Aren't these [0] lines wrong?

"[\\b\\d][Aa]bbo[\\bA-Z\\d]",

\b inside a set (square brackets) is a backspace character [1], not a word boundary. I don't think it was intended? Or is the regex flavor used here different?

[0] https://github.com/BlueFalconHD/apple_generative_model_safet...

[1] https://developer.apple.com/documentation/foundation/nsregul...

replies(1): >>44491264 #
2. BlueFalconHD ◴[07 Jul 25 15:16 UTC] No.44491264[source]▶
The framework loading these is in Swift. I haven’t gotten around to the logic for the JSON/regex parsing but ChatGPT seems to understand the regexes just fine