(github.com)

534 points BlueFalconHD | 1 comments | 06 Jul 25 19:50 UTC | HN request time: 0.212s | 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

torginus ◴[06 Jul 25 21:31 UTC] No.44484236[source]▶

>>44483485 (OP) #

I find it funny that AGI is supposed to be right around the corner, while these supposedly super smart LLMs still need to get their outputs filtered by regexes.

replies(8): >>44484268 #>>44484323 #>>44484354 #>>44485047 #>>44485237 #>>44486883 #>>44487765 #>>44493460 #

jonas21 ◴[06 Jul 25 21:39 UTC] No.44484323[source]▶

>>44484236 #

I don't think anyone believes Apple's LLMs are anywhere near state of the art (and certainly not their on-device LLMs).

replies(1): >>44484929 #

1. lupire ◴[06 Jul 25 23:02 UTC] No.44484929[source]▶

>>44484323 #

Apple isn't the only one doing this.

↑

I extracted the safety filters from Apple Intelligence models