←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: 0.284s | 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
trebligdivad ◴[06 Jul 25 20:56 UTC] No.44483981[source]▶
Some of the combinations are a bit weird, This one has lots of stuff avoiding death....together with a set ensuring all the Apple brands have the correct capitalisation. Priorities hey!

https://github.com/BlueFalconHD/apple_generative_model_safet...

replies(11): >>44483999 #>>44484073 #>>44484095 #>>44484410 #>>44484636 #>>44486072 #>>44487916 #>>44488185 #>>44488279 #>>44488362 #>>44488856 #
grues-dinner ◴[06 Jul 25 21:09 UTC] No.44484073[source]▶
Interesting that it didn't seem to include "unalive".

Which as a phenomenon is so very telling that no one actually cares what people are really saying. Everyone, including the platforms knows what that means. It's all performative.

replies(11): >>44484164 #>>44484360 #>>44484635 #>>44484665 #>>44485033 #>>44485034 #>>44486246 #>>44487244 #>>44488055 #>>44488114 #>>44500918 #
j-krieger ◴[07 Jul 25 08:45 UTC] No.44488114[source]▶
It's also a shining example of American puritanism. Asian models or those in Europe are far less censored.
replies(6): >>44488741 #>>44488993 #>>44489194 #>>44489626 #>>44489822 #>>44491464 #
reaperducer[dead post] ◴[07 Jul 25 11:11 UTC] No.44488993[source]▶
[flagged]
1. ryx ◴[07 Jul 25 14:54 UTC] No.44491024[source]▶
To be more precise - the puritans fled from Europe to the New World because Europe became too modern and less conservative for them, starting with Martin Luther and the following Reformation and Age of Enlightenment. The social effects on the American society are heavily noticeable until today, but I leave this exercise to the reader.