←back to thread

I extracted the safety filters from Apple Intelligence models

(github.com)
534 points BlueFalconHD | 2 comments | 06 Jul 25 19:50 UTC | HN request time: 0.001s | 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
userbinator ◴[06 Jul 25 22:00 UTC] No.44484484[source]▶
China calls it "harmonious society", we call it "safety". Censorship by any other name would be just as effective for manipulating the thoughts of the populace. It's not often that you get to see stuff like this.
replies(4): >>44484542 #>>44485060 #>>44487180 #>>44487705 #
energy123 ◴[07 Jul 25 05:52 UTC] No.44487180[source]▶
This is the rhetorical tactic of false equivalence. State censorship by an autocracy with the objective of population control is not the same thing as a private company inside a democracy censoring their product to avoid bad press and maintain goodwill for shareholders. If you want solid proof that it's not the same thing, see all the uncensored open weights models that you can freely download and use without fear of persecution.
replies(3): >>44487393 #>>44488175 #>>44506210 #
Hackbraten ◴[07 Jul 25 08:56 UTC] No.44488175[source]▶
But who of the general populace has the technical skill to replace their on-device assistant with a free one? And that's if Apple even allows that?

In practice, there's not that much difference between a megacorporate monopolist and a state.

replies(2): >>44488466 #>>44488959 #
1. energy123 ◴[07 Jul 25 09:41 UTC] No.44488466[source]▶
I think there are big differences, such as whether or not you go to prison. Those differences are obfuscated when we use language like "megacorporate monopolist" or "scifi dystopia". Instead of using these abstract labels that attempt to categorize different things into homogeneous buckets that have preexisting moral valence, which is a good rhetorical strategy but a poor strategy for understanding, simply describe what is actually happening at a sufficient level of detail without judgement. We would gain a clearer understanding, which is needed to identify the real problems, such as what Meta is doing to our civic fabric, not some unimportant thing that Apple is doing to its nascent LLM that has 0% market share.
replies(1): >>44489596 #
2. Hackbraten ◴[07 Jul 25 12:20 UTC] No.44489596[source]▶
You're saying that as if Apple's LLM somehow were the exception.

No matter if we want it or not, life and cultural exchange increasingly happens on Tiktok, Instagram and the like. One thing that all those platforms have in common is that they disallow their users worldwide to have any meaningful discourse on e.g. sex, rape, and suicide. Don't you think that it's important, perhaps more important than ever before, for teenagers to be able to inform themselves about these topics?