←back to thread

I extracted the safety filters from Apple Intelligence models

(github.com)
536 points BlueFalconHD | 5 comments | 06 Jul 25 19:50 UTC | HN request time: 0.622s | 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 #
Rebelgecko ◴[06 Jul 25 23:59 UTC] No.44485309[source]▶
This is somewhat related to the concept of the "euphemism treadmill":

the matter-of-fact term of today becomes the pejorative of tomorrow so a new term is invented to avoid the negative connotation of the original term. Then eventually the new term becomes a pejorative and the cycle continues.

replies(2): >>44488172 #>>44492807 #
1. dkdbejwi383 ◴[07 Jul 25 08:56 UTC] No.44488172[source]▶
It has been suggested - although I am unsure if there is strong evidence - that the word "bear" is a euphemism along these lines, meaning "brown one" for the since-forgotten original name for the animal, as it was allegedly believed to be either too frightful to say aloud, or would summon a bear.
replies(2): >>44488468 #>>44488547 #
2. ben_w ◴[07 Jul 25 09:41 UTC] No.44488468[source]▶
While it's conceivable (consider phrases such as "speak of the devil and he shall appear" and similar phrases in other languages), I would also say the etymology of names for things are often at the same level as "brown one":

  • Horse, ultimately from Proto-Indo-European *ḱers-, “to run”
  • Planet, from Ancient Greek πλανήτης (planḗtēs), “wanderer”
  • Lots of Latin-derived words, companion (bread together), conspire (breathe together), transgression (step across), etc.
  • Hamburger the food named after the city of Hamburg, where "burg" means "castle", because it had a castle
  • My forename means "son of the right/south" or "son of days", my family name means "wheat field/clearing" (in a different language); where "wheat" itself comes from Proto-Germanic, from *hwītaz (“white”) and the "ley" part from Proto-Indo-European *lówkos (“clearing”), derived from *lewk- (“bright”), and *lewk-  also gives all these derived terms even just in English:
https://en.wiktionary.org/wiki/Category:English_terms_derive...
3. 0points ◴[07 Jul 25 09:55 UTC] No.44488547[source]▶
It's not suggested, the historic use of noa words is a fact.

See https://en.wikipedia.org/wiki/Noa-name

replies(2): >>44491054 #>>44503895 #
4. dkdbejwi383 ◴[07 Jul 25 14:56 UTC] No.44491054[source]▶
I mean suggested in the sense that this specific example cannot be evidenced, as there aren't any primary sources from that time we can refer to.
5. spookie ◴[08 Jul 25 20:41 UTC] No.44503895[source]▶
Oh! Cape of Good Hope was renamed that way when portuguese mariners discovered they could go around the areas more susceptible to "freak waves".

This is a problem even today, some have said it is due to hotter currents coming from the Indian ocean meeting the cold Atlantic. But the judge is still out on that one.

Good documentary on rogue waves: https://www.youtube.com/watch?v=EfNc_6EjbMU