←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: 0.833s | 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
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 #
mmaunder ◴[06 Jul 25 21:35 UTC] No.44484284[source]▶
As does:

   "(?i)\\bAnthony\\s+Albanese\\b",
    "(?i)\\bBoris\\s+Johnson\\b",
    "(?i)\\bChristopher\\s+Luxon\\b",
    "(?i)\\bCyril\\s+Ramaphosa\\b",
    "(?i)\\bJacinda\\s+Arden\\b",
    "(?i)\\bJacob\\s+Zuma\\b",
    "(?i)\\bJohn\\s+Steenhuisen\\b",
    "(?i)\\bJustin\\s+Trudeau\\b",
    "(?i)\\bKeir\\s+Starmer\\b",
    "(?i)\\bLiz\\s+Truss\\b",
    "(?i)\\bMichael\\s+D\\.\\s+Higgins\\b",
    "(?i)\\bRishi\\s+Sunak\\b",
https://github.com/BlueFalconHD/apple_generative_model_safet...

Edit: I have no doubt South African news media are going to be in a frenzy when they realize Apple took notice of South African politicians. (Referring to Steenhuisen and Ramaphosa specifically)

replies(6): >>44484366 #>>44484419 #>>44484695 #>>44484709 #>>44484883 #>>44487192 #
1. skissane ◴[06 Jul 25 22:29 UTC] No.44484695[source]▶
The problem with blocking names of politicians: the list of “notable politicians” is not only highly country-specific, it is also constantly changing-someone who is a near nobody today in a few more years could be a major world leader (witness the phenomenal rise of Barack Obama from yet another state senator in 2004-there’s close to 2000 of them-to US President 5 years later.) Will they put in the ongoing effort to constantly keep this list up to date?

Then there’s the problem of non-politicians who coincidentally have the same as politicians - witness 1990s/2000s Australia, where John Howard was Prime Minister, and simultaneously John Howard was an actor on popular Australian TV dramas (two different John Howards, of course)

replies(1): >>44484782 #
2. idkfasayer ◴[06 Jul 25 22:42 UTC] No.44484782[source]▶
Fun fact: There was at least on dip in Berkshire Hathaway stock, when Anne Hathaway got sick
replies(2): >>44484916 #>>44488065 #
3. lupire ◴[06 Jul 25 23:00 UTC] No.44484916[source]▶
Was she eating at Jimmy's Buffet?
4. extraduder_ire ◴[07 Jul 25 08:39 UTC] No.44488065[source]▶
Even if your keyword searching trading bot is smart enough to know it's unrelated, knowing there's dumber bots out there is information you can base trades on.