←back to thread

534 points BlueFalconHD | 1 comments | | 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.
Show context
bombcar ◴[] No.44483830[source]
There’s got to be a way to turn these lists of “naughty words” into shibboleths somehow.
replies(2): >>44484345 #>>44485000 #
1. spydum ◴[] No.44484345[source]
Love idea, but I think there are simply too many models to make it practical?