Earlier quoted context omitted.
I think that’s because she’s been victim of a lot of deep fake porn
How does this explain Boris Johnson or Liz Truss?
I’m telling you, some people have weird fantasies…
I extracted the safety filters from Apple Intelligence models
51–60 of 455 posts
Re: I extracted the safety filters from Apple Intelligence models
#52Some 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...
Don’t be so judgmental. People in corporate America do have their priorities right!
Re: I extracted the safety filters from Apple Intelligence models
#53Alexandra Ocasio Cortez triggers a violation? https://github.com/BlueFalconHD/apple_generative_model_safet...
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_…
I'm not surprised that anything political is being filtered, but this should definitely provoke some deep consideration around who has control of this stuff.
Re: I extracted the safety filters from Apple Intelligence models
#54I think these are test data and not actual safety filters. https://github.com/BlueFalconHD/apple_generative_model_safet...
There is definitely some testing stuff in here (e.g. the “Granular Mango Serpent” one) but there are real rules. Also if you test phrases matched by the regexes with generation (via Shortcuts or Foundation Models Framework) the blocklists are definitely applied.
This specific file you’ve referenced is rhetorical v1 format which solely handles substitution. It substitutes the offensive term with “test complete”
Re: I extracted the safety filters from Apple Intelligence models
#55I find it funny that AGI is supposed to be right around the corner, while these supposedly super smart LLMs still need to get their outputs filtered by regexes.
This is just policy and alignment from Apple. Just because the Internet says a bunch of junk doesn't mean you want your model spewing it.
sure but models also can't see any truth on their own. They are literally butchered and lobotomized with filters and such. Even high IQ people struggle with certain truth after reading a lot, how is these models going to find it with so much filters?
Re: I extracted the safety filters from Apple Intelligence models
#56Are you sure it's fully deobfuscated? What's up with reject phrases like "Granular mango serpent"?
These are the contents read by the Obfuscation functions exactly. There seems to be a lot of testing stuff still though, remember these models are relatively recent. There is a true safety model being applied after these checks as well, this is just to catch things before needing to load the safety model.
Re: I extracted the safety filters from Apple Intelligence models
#57Re: I extracted the safety filters from Apple Intelligence models
#58Some of the data for locale "CN" has a long list of forbidden phrases. Broad coverage of words related to sexual deviancy, as expected. Not much on the political side, other than blocks on religious subjects.[1]
This may be test data. Found
"golliwog": "test complete"
Re: I extracted the safety filters from Apple Intelligence models
#59China 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.
Re: I extracted the safety filters from Apple Intelligence models
#60Are you sure it's fully deobfuscated? What's up with reject phrases like "Granular mango serpent"?
Maybe it's used to verify that the filter is loaded.