(github.com)

534 points BlueFalconHD | 2 comments | 06 Jul 25 19:50 UTC | HN request time: 0.544s | 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

mike_hearn ◴[06 Jul 25 20:38 UTC] No.44483836[source]▶

>>44483485 (OP) #

Are you sure it's fully deobfuscated? What's up with reject phrases like "Granular mango serpent"?

replies(9): >>44483870 #>>44483918 #>>44483982 #>>44484014 #>>44484047 #>>44484460 #>>44484489 #>>44486400 #>>44488390 #

1. airstrike ◴[06 Jul 25 20:48 UTC] No.44483918[source]▶

>>44483836 #

the one at the bottom of the README spells out xcode

wyvern illustrous laments darkness

replies(1): >>44484213 #

2. cwmoore ◴[06 Jul 25 21:28 UTC] No.44484213[source]▶

>>44483918 (TP) #

read every good expletive “xxx”

↑

I extracted the safety filters from Apple Intelligence models