←back to thread

I extracted the safety filters from Apple Intelligence models

(github.com)
536 points BlueFalconHD | 1 comments | 06 Jul 25 19:50 UTC | HN request time: 0.21s | 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
MatekCopatek ◴[07 Jul 25 12:56 UTC] No.44489915[source]▶
You can design a racist propaganda poster, put someone's face onto a porn pic or manipulate evidence with photoshop. Apart from super specific things like trying to print money, the tool doesn't stop you from doing things most people would consider distasteful, creepy or even illegal.

So why are we doing this now? Has anything changed fundamentally? Why can't we let software do everything and then blame the user for doing bad things?

replies(2): >>44489943 #>>44490018 #
1. MisterTea ◴[07 Jul 25 13:08 UTC] No.44490018[source]▶
What's hard to understand here? Those tools require skill and time to develop. AI makes things like those racist posters and revenge porn completely effortless and instant.