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

141–150 of 455 posts

Re: I extracted the safety filters from Apple Intelligence models

#141

Post by derefr »

qingcharles wrote: post #25
grues-dinner wrote: post #19

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?

> At what point do the new words become the actual words?

Presumably, for this use-case, that would come at exactly the point where using “unalive” as a keyword in an image-generation prompt generates an image that Apple wouldn’t appreciate.

Re: I extracted the safety filters from Apple Intelligence models

#142

Post by fastball »

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.

To be fair, there are people who I sometimes wish I could filter with regex.

Re: I extracted the safety filters from Apple Intelligence models

#143

Post by montagg »

qingcharles wrote: post #25
grues-dinner wrote: post #19

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?

They become the “real words” later. This is the way all trust & safety works. It’s an evolution over time. Adding some friction does improve things, but some people will always try to get around the filters. Doesn’t mean it’s simply performative or one shouldn’t try.

Re: I extracted the safety filters from Apple Intelligence models

#144

Post by Auracle »

baxtr wrote: post #51
HeckFeck wrote: post #40

Earlier quoted context omitted.

How does this explain Boris Johnson or Liz Truss?

I’m telling you, some people have weird fantasies…

Now that they've cleaned it up it isn't so bad, but browse Civit.ai a bit and that'll still be confirmed - just not with real people anymore.

Re: I extracted the safety filters from Apple Intelligence models

#145

Post by avianlyric »

pyuser583 wrote: post #140
avianlyric wrote: post #121

Earlier quoted context omitted.

> A while back a British politician was “de-banked” and his bank denied it. That’s extremely wrong. Cry me a river. I’ve worked in banks in the team making exactly these kinds of decisions. Trust me Nigel Farage knew exactly what happened and why. NatWest never denied it to the public, because they originally refused to comment on it. Commenting on the specifics details of a customer would be a horrific breach of cus…

> NatWest never denied it to the public, because they originally refused to comment on it. Are you saying that Alison Rose did not leak to the BBC? Why was she forced to resign? I thought it was because she leaked false information to the press. This isn’t a diversion. It’s exactly the problem with not being transparent. Of course Farage knew what happened, but how could he convince the public (he’s a public figure),…

> Why was she forced to resign? I thought it was because she leaked false information to the press.

She was forced to resign because she leaked, the content of the leak was utterly immaterial. The simple fact she leaked was an automatically fireable offence, it doesn’t matter a jot if she lied or not. Customer privacy is non-negotiable when you’re bank. Banks aren’t number 10, the basic expectation is that customer information is never handed out, except to the customer, in response to a court order, or the belief that there is an immediate threat to life.

Do you honestly think that it’s okay for banks to discuss the private banking details of their customers with the press?

Re: I extracted the safety filters from Apple Intelligence models

#146

Post by Rebelgecko »

qingcharles wrote: post #25
grues-dinner wrote: post #19

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 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.

Re: I extracted the safety filters from Apple Intelligence models

#147

Post by SV_BubbleTime »

Waterluvian wrote: post #135
Terr_ wrote: post #111

Earlier quoted context omitted.

> There's no way to stay ahead of the new language that people create. I'm imagining a new exploit: After someone says something totally innocent, people gang up in the comments to act like a terrible vicious slur has been said, and then the moderation system (with an LLM involved somewhere) "learns" that an arbitrary term is heinous eand indirectly bans any discussion of that topic.

Hey I was pro-skub waaaay before all the anti-skub people switched sides.

How dare you use that word. My parents died in the Eastasin Civil war so that I could live freely without you people calling us that.

Re: I extracted the safety filters from Apple Intelligence models

#148

Post by avianlyric »

furyofantares wrote: post #137
avianlyric wrote: post #103

Earlier quoted context omitted.

I think gen AI is radically different to tools like photoshops or similar. In the past it was always extremely clear that the creator of content was the person operating the computer. Gen AI changes that, regardless of if your views on authorship of gen AI content. The simple fact is that the vast majority of people consider Gen AI output to be authored by the machine that generated it, and by extension the company t…

> The simple fact is that the vast majority of people consider Gen AI output to be authored by the machine that generated it They do? I routinely see people say "Here's an xyz I generated." They are stating that they did the do-ing, and the machine's role is implicitly acknowledged in the same was as a camera. And I'd be shocked if people didn't have a sense of authorship of the idea, as well as an increasing sense o…

Yes people will happily claim authorship over AI output when it’s in their favour. They will equally disclaim authorship if it allows them to express a view while avoiding the consequences of expressing that view.

I don’t think it’s hard to believe that the press wouldn’t have a field day if someone managed to get Apple Gen AI stuff to express something racist, or equally abusive.

Case in point, article about how Google’s Veo 3 model is being used to flood TikTok with racist content:

https://arstechnica.com/ai/2025/07/racist-ai-videos-created-...

Re: I extracted the safety filters from Apple Intelligence models

#149

Post by avianlyric »

tjwebbnorfolk wrote: post #119
avianlyric wrote: post #89

Earlier quoted context omitted.

Why is this wrong? Applying special treatment to politically exposed persons has been standard practice in every high risk industry for a very long time. The simple fact is that people get extremely emotional about politicians, politicians both receive obscene amounts of abuse, and have repeatedly demonstrated they’re not above weaponising tools like this for their own goals. Seems perfectly reasonable that Apple doe…

I can Google for any of these people, and I can get real results with real information.

You would hope that search would be a politically safe space to operate. But politicians find a way to ruin everything for short term political gain.

https://arstechnica.com/tech-policy/2018/12/republicans-in-c...

Re: I extracted the safety filters from Apple Intelligence models

#150

Post by tbrownaw »

Terr_ wrote: post #111
qingcharles wrote: post #25

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?

> There's no way to stay ahead of the new language that people create. I'm imagining a new exploit: After someone says something totally innocent, people gang up in the comments to act like a terrible vicious slur has been said, and then the moderation system (with an LLM involved somewhere) "learns" that an arbitrary term is heinous eand indirectly bans any discussion of that topic.

I'm pretty sure this can work human moderators rather than an LLM, too.
Post reply on HN