Live data from Hacker News

I extracted the safety filters from Apple Intelligence models

github.com

31–40 of 455 posts

Re: I extracted the safety filters from Apple Intelligence models

#31

Earlier quoted context omitted.

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.

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?

This question is sort of the same as asking why the universal translator wasn't able to translate the metaphor language of the Star Trek episode Darmok. Surely if the metaphor has become the first order meaning then there's no litteral meaning anymore.

Re: I extracted the safety filters from Apple Intelligence models

#32

Earlier quoted context omitted.

Legal requirement to maintain a trademark.

In what way would (A|a)pple's own AI writing "imac" endanger the trademark? Is capitalisation even part of a word-based trademark? I'm more surprised they don't have a rule to do that rather grating s/the iPhone/iPhone/ transform (or maybe it's in a different file?).

Yes, proper nouns are capitalized.

And of course it's much worse for a company's published works to not respect branding-- a trademark only exists if it is actively defended. Official marketing material by a company has been used as legal evidence that their trademark has been genericized:

>In one example, the Otis Elevator Company's trademark of the word "escalator" was cancelled following a petition from Toledo-based Haughton Elevator Company. In rejecting an appeal from Otis, an examiner from the United States Patent and Trademark Office cited the company's own use of the term "escalator" alongside the generic term "elevator" in multiple advertisements without any trademark significance.[8]

https://en.wikipedia.org/wiki/Generic_trademark

Re: I extracted the safety filters from Apple Intelligence models

#34
post #30

Alexandra Ocasio Cortez triggers a violation? https://github.com/BlueFalconHD/apple_generative_model_safet...

Perhaps in context? Maybe the training data picked up on her name as potentially used as a "slur" associated with her race. Wonder if there are others I know I can look.

Re: I extracted the safety filters from Apple Intelligence models

#36

Earlier quoted context omitted.

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?

It depends on if you think that something is less real because it’s transmitted digitally.

No, I'm only thinking that we're not permitted in a lot of digital spaces to use the banned words (e.g. suicide), but IRL doesn't generally have those limits. Is there a point where we use the censored word so much that it spills over into the real world?

Re: I extracted the safety filters from Apple Intelligence models

#37

I 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.

Re: I extracted the safety filters from Apple Intelligence models

#38

Earlier quoted context omitted.

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?

This question is sort of the same as asking why the universal translator wasn't able to translate the metaphor language of the Star Trek episode Darmok. Surely if the metaphor has become the first order meaning then there's no litteral meaning anymore.

I guess, so far, the people inventing the words have left the meaning clear with things like "un-alive" which is readable even to someone coming across it for the first time.

Your point stands when we start replacing the banned words with things like "suicide" for "donkeyrhubarb" and then the walls really will fall.

Re: I extracted the safety filters from Apple Intelligence models

#39
post #30

Alexandra 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_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)

Re: I extracted the safety filters from Apple Intelligence models

#40
post #35
post #30

Alexandra Ocasio Cortez triggers a violation? https://github.com/BlueFalconHD/apple_generative_model_safet...

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?
Post reply on HN