←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: 0s | 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.
Show context
trebligdivad ◴[06 Jul 25 20:56 UTC] No.44483981[source]▶
Some of the combinations are a bit weird, This one has lots of stuff avoiding death....together with a set ensuring all the Apple brands have the correct capitalisation. Priorities hey!

https://github.com/BlueFalconHD/apple_generative_model_safet...

replies(11): >>44483999 #>>44484073 #>>44484095 #>>44484410 #>>44484636 #>>44486072 #>>44487916 #>>44488185 #>>44488279 #>>44488362 #>>44488856 #
andy99 ◴[06 Jul 25 20:58 UTC] No.44483999[source]▶
> Apple brands have the correct capitalisation. Priorities hey!

To me that's really embarrassing and insecure. But I'm sure for branding people it's very important.

replies(2): >>44484013 #>>44488381 #
1. whywhywhywhy ◴[07 Jul 25 09:27 UTC] No.44488381[source]▶
To be fair to the developers it's something an Apple exec is gonna point out when demoed the tech and complain about. They've always taken brand capitalization and grammar around their products seriously.