(github.com)

534 points BlueFalconHD | 1 comments | 06 Jul 25 19:50 UTC | HN request time: 0.27s | 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

bawana ◴[06 Jul 25 21:28 UTC] No.44484214[source]▶

>>44483485 (OP) #

Alexandra Ocasio Cortez triggers a violation?

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

replies(7): >>44484242 #>>44484256 #>>44484284 #>>44484352 #>>44484528 #>>44485841 #>>44488050 #

1. FateOfNations ◴[06 Jul 25 21:44 UTC] No.44484352[source]▶

>>44484214 #

interesting, that's specifically in the Spanish localization.

↑

I extracted the safety filters from Apple Intelligence models