←back to thread

I extracted the safety filters from Apple Intelligence models

(github.com)
536 points BlueFalconHD | 2 comments | 06 Jul 25 19:50 UTC | HN request time: 0.485s | 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 #
andy99 ◴[06 Jul 25 20:58 UTC] No.44483999[source]▶
> Apple brands have the correct capitalisation. Priorities hey!

To me that's really embarrassing and insecure. But I'm sure for branding people it's very important.

replies(2): >>44484013 #>>44488381 #
WillAdams ◴[06 Jul 25 21:00 UTC] No.44484013[source]▶
Legal requirement to maintain a trademark.
replies(3): >>44484149 #>>44485570 #>>44485667 #
1. lxgr ◴[07 Jul 25 00:44 UTC] No.44485570[source]▶
In their own marketing language, sure, but to force this on their users' speech?

Consider that these models, among other things, power features such as "proofread" or "rewrite professionally".

replies(1): >>44485687 #
2. ◴[07 Jul 25 01:05 UTC] No.44485687[source]▶