←back to thread

I extracted the safety filters from Apple Intelligence models

(github.com)
534 points BlueFalconHD | 7 comments | 06 Jul 25 19:50 UTC | HN request time: 0.001s | source | bottom

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
bawana ◴[06 Jul 25 21:28 UTC] No.44484214[source]▶
Alexandra Ocasio Cortez triggers a violation?

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

replies(7): >>44484242 #>>44484256 #>>44484284 #>>44484352 #>>44484528 #>>44485841 #>>44488050 #
cpa ◴[06 Jul 25 21:33 UTC] No.44484256[source]▶
I think that’s because she’s been victim of a lot of deep fake porn
replies(1): >>44484294 #
1. HeckFeck ◴[06 Jul 25 21:36 UTC] No.44484294[source]▶
How does this explain Boris Johnson or Liz Truss?
replies(4): >>44484385 #>>44484397 #>>44484671 #>>44487987 #
2. AlphaAndOmega0 ◴[06 Jul 25 21:48 UTC] No.44484385[source]▶
I can only imagine that people would pay to not see porn of either individual.
3. baxtr ◴[06 Jul 25 21:49 UTC] No.44484397[source]▶
I’m telling you, some people have weird fantasies…
replies(1): >>44485278 #
4. Aeolun ◴[06 Jul 25 22:25 UTC] No.44484671[source]▶
Put them together in the same prompt?
5. AuryGlenz ◴[06 Jul 25 23:54 UTC] No.44485278[source]▶
Now that they've cleaned it up it isn't so bad, but browse Civit.ai a bit and that'll still be confirmed - just not with real people anymore.
replies(1): >>44486238 #
6. SV_BubbleTime ◴[07 Jul 25 02:37 UTC] No.44486238{3}[source]▶
I’m convinced there are a dozen deviants on Covid with a hundred new accounts per month posting their perversion in order to make it seem more commonplace.

No porn site has that much extremely X or Y stuff.

Someone is using the internets newest porn site to push a sexual agenda.

7. blitzar ◴[07 Jul 25 08:28 UTC] No.44487987[source]▶
Rule 34