←back to thread

I extracted the safety filters from Apple Intelligence models

(github.com)
534 points BlueFalconHD | 4 comments | 06 Jul 25 19:50 UTC | HN request time: 0.834s | 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 #
qingcharles ◴[06 Jul 25 21:22 UTC] No.44484164[source]▶
It's totally performative. There's no way to stay ahead of the new language that people create.

At what point do the new words become the actual words? Are there many instances of people using unalive IRL?

replies(17): >>44484171 #>>44484218 #>>44484614 #>>44484958 #>>44484970 #>>44484989 #>>44485202 #>>44485277 #>>44485309 #>>44486128 #>>44486394 #>>44487625 #>>44487839 #>>44487936 #>>44488097 #>>44488704 #>>44493436 #
1. blitzar ◴[07 Jul 25 08:21 UTC] No.44487936[source]▶
Always has been, nothing is new.

You can't say fuck on tv, but you can say fudge as a 1 for 1 replacement. You cant show people having sex, but you can show them walking into a bedroom and then cut to 30 seconds later and they are having a cigarette in bed.

Now after the influence of TV and Movies ... is Vaping after sex a thing?

replies(1): >>44489654 #
2. stripline ◴[07 Jul 25 12:27 UTC] No.44489654[source]▶
My kids watch streamers on YouTube and the common replacement is “frick”. It’s said so often that they started using it saying things like “what the frick!?” so I had to explain to them that’s essentially the same as using the real word.
replies(1): >>44496886 #
3. qingcharles ◴[08 Jul 25 03:49 UTC] No.44496886[source]▶
I wonder why they didn't just use the "frack" from BSG?
replies(1): >>44506892 #
4. blitzar ◴[09 Jul 25 06:29 UTC] No.44506892{3}[source]▶
Takes a person of culture to watch BSG