I extracted the safety filters from Apple Intelligence models

Post by binarymax » Mon, Jul 07, 2025, 12:11 AM UTC

XorNot wrote: post #43

tpmoney wrote: post #27

Earlier quoted context omitted.

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 rejec…

Post by pyman » Mon, Jul 07, 2025, 12:28 AM UTC

tbrownaw wrote: post #150

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.

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

Post by userbinator » Mon, Jul 07, 2025, 12:42 AM UTC

madeofpalk wrote: post #69

userbinator wrote: post #59

China 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.

I don't think it's controversial or unsurprising at all that a company doesn't want their random sentence generator to spit out 'brand damaging' sentences. You know the field day media would have Apple's new feature summarises a text message as "Jane thinks Anthony Albanese should die".

Post by durkie » Mon, Jul 07, 2025, 12:48 AM UTC

cyanydeez wrote: post #124

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.

yo, these are businesses. It's not performative, its CYA. They care because of legal reasons, not moral or ethical.

Post by lxgr » Mon, Jul 07, 2025, 12:57 AM UTC

sbierwagen wrote: post #32

grues-dinner wrote: post #23

Earlier quoted context omitted.

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-bas…