Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I extracted the safety filters from Apple Intelligence models

github.com

Post reply on HN
Print view View original

41–50 of 455 posts

Re: I extracted the safety filters from Apple Intelligence models

#41

Post by bigyabai »

binarymax wrote: post #9

Wow, this is pretty silly. If things are like this at Apple I’m not sure what to think. https://github.com/BlueFalconHD/apple_generative_model_safet... EDIT: just to be clear, things like this are easily bypassed. “Boris Johnson”=>”B0ris Johnson” will skip right over the regex and will be recognized just fine by an LLM.

> If things are like this at Apple I’m not sure what to think.

I don't know what you expected? This is the SOTA solution, and Apple is barely in the AI race as-is. It makes more sense for them to copy what works than to bet the farm on a courageous feature nobody likes.

Re: I extracted the safety filters from Apple Intelligence models

#42

Post by jonas21 »

torginus wrote: post #33

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.

I don't think anyone believes Apple's LLMs are anywhere near state of the art (and certainly not their on-device LLMs).

Re: I extracted the safety filters from Apple Intelligence models

#43

Post by XorNot »

tpmoney wrote: post #27
binarymax wrote: post #9

Wow, this is pretty silly. If things are like this at Apple I’m not sure what to think. https://github.com/BlueFalconHD/apple_generative_model_safet... EDIT: just to be clear, things like this are easily bypassed. “Boris Johnson”=>”B0ris Johnson” will skip right over the regex and will be recognized just fine by an LLM.

I doubt the purpose here is so much to prevent someone from intentionally side stepping the block. It's more likely here to avoid the sort of headlines you would expect to see if someone was suggested "I wish ${politician} would die" as a response to an email mentioning that politician. In general you should view these sorts of broad word filters as looking to short circuit the "think of the children" reactions to Ti…

It would also substantially disrupt the generation process: a model which sees B0ris and not Boris is going to struggle to actually associate that input to the politician since it won't be well represented in the training set (and on the output side the same: if it does make the association, a reasoning model for example would include the proper name in the output first at which point the supervisor process can reject it).

Re: I extracted the safety filters from Apple Intelligence models

#47

Post by hulium »

grues-dinner wrote: post #19
trebligdivad wrote: post #10

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...

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.

Seems more like it should stop the AI from e.g. summarizing news and emails about death, not for a chat filter.

Re: I extracted the safety filters from Apple Intelligence models

#48

Post by armchairhacker »

mmaunder wrote: post #39
bawana wrote: 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_…

Also “Biden” and “Trump” but the regex is different.

https://github.com/BlueFalconHD/apple_generative_model_safet...

https://github.com/BlueFalconHD/apple_generative_model_safet...

Re: I extracted the safety filters from Apple Intelligence models

#50

Post by AlphaAndOmega0 »

HeckFeck wrote: post #40
cpa wrote: post #35

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 can only imagine that people would pay to not see porn of either individual.
Post reply on HN