(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

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 #

michaelt ◴[06 Jul 25 22:08 UTC] No.44484528[source]▶

>>44484214 #

I assume all the corporate GenAI models have blocks for "photorealistic image of <politician name> being arrested", "<politician name> waving ISIS flag", "<politician name> punching baby" and suchlike.

replies(2): >>44484622 #>>44484876 #

1. bigyabai ◴[06 Jul 25 22:54 UTC] No.44484876[source]▶

>>44484528 #

Particularly the models owned by CEOs who suck-up to authoritarianism, one could imagine.

↑

I extracted the safety filters from Apple Intelligence models