←back to thread

534 points BlueFalconHD | 1 comments | | HN request time: 0.241s | 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. BlueFalconHD ◴[] No.44484380[source]
One additional note for everyone is that this is an additional safety step on top of the safety model, so this isn’t exhaustive, there is plenty more that the actual safety model catches, and those can’t easily be extracted.