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

Apple Intelligence Foundation Language Models Tech Report 2025

machinelearning.apple.com

Post reply on HN
Print view View original

171–180 of 210 posts

Re: Apple Intelligence Foundation Language Models Tech Report 2025

#171

Post by lxgr »

al_borland wrote: post #167
lxgr wrote: post #126

Earlier quoted context omitted.

> It seems like a very unnatural way to pose those two questions. Most humans would trip on that I'd assume GP only gave an example. As a pretty frequent user, I can unfortunately only confirm that Siri trips over almost every multi-part question. This would be forgivable if there weren't multiple voice-based AI consumer products available that can handle these kinds of requests perfectly.

And Apple has integrated one of them, ChatGPT, to do just that. If they wanted an LLM answer they could have got one. They went out of their way just to take shots at Apple.

I can’t talk to ChatGPT hands-free on my Apple devices, but I can to ChatGPT.

Besides that, many people don’t install any apps, and Apple not pre-installing a reasonable LLM to cater to that market just seems incredibly out of character.

And there’s enough credible reporting and personnel reshuffling happening to suggest that it’s not available yet because they failed to make it work, not because they didn’t try.

Re: Apple Intelligence Foundation Language Models Tech Report 2025

#172

Post by snowwrestler »

bitpush wrote: post #111
slashnode wrote: post #104

Earlier quoted context omitted.

I think it's the right strategy for Apple. They're not a model company. The risks of deploying something half-baked to their users is unacceptable. They're taking it slow and trying to do it in a way that doesn't damage/erode their brand. Wait it out, let the best model(s) rise to the surface (and the hallucination problems to get sufficiently mitigated), and then either partner with a proprietary provider or deploy…

This is a reasonable approach, but unfortunately misses what made Apple soooo successful. Apple is the master of controlling the brand. Apple DOES NOT like to highlight their suppliers. Nobody knows who makes iPhones displays, or sensors, or RAMs. They love to "invent" brands that they control, so that they can commodotize the underlying supplier. Hey user, it is a retina display and dont worry whether it is LG or Sa…

Please go rewatch the iPhone keynote by Steve Jobs. Everyone remembers the beginning; few seem to remember that he brings out 3 other CEOs to highlight the integrations between the iPhone and those companies.

Or consider that they spent a decade highlighting that their computers were powered by Intel, after leaving their proprietary PowerPC architecture—again, under Steve Jobs.

Or go all the way back to 1997 when Steve Jobs had Bill Gates on the screen at Macworld and announced that IE would be the default browser on Mac.

It’s easy to fall into a caricature of Apple, where they insist on making everything themselves. What is more accurate is to say that they are not afraid to make things themselves, when they think they have a better idea. But they are also not afraid to do deals when it is the best way forward right now.

Re: Apple Intelligence Foundation Language Models Tech Report 2025

#173

Post by stogot »

danhau wrote: post #168
jamesrcole wrote: post #152

Earlier quoted context omitted.

A tool that can handle more than one question at a time is useful. Modern LLMs handle that with ease. So it's completely reasonable to be critical of that limitation.

Why is Siri being discussed in the context of LLMs and Apple Intelligence? Have they already released Siri 2.0 or am I missing something?

The OP is making a point that Apple is behind. They might be publishing research, but it’s completely useless to the end user buying their products.

Re: Apple Intelligence Foundation Language Models Tech Report 2025

#174

Post by devinprater »

Lol and yet, Google has AI image descriptions in their screen reader, TalkBack, before Apple. Apple is supposed to be the accessibility king. But with AI, they just can't, even if they obviously have access to ChatGPT which has vision capabilities. Granted, I don't know what model Google uses because tech news don't do Android Accessibility Suite APK teardowns, but it works pretty well, and fast too.

Re: Apple Intelligence Foundation Language Models Tech Report 2025

#175

Post by stogot »

al_borland wrote: post #166
jamesrcole wrote: post #152

Earlier quoted context omitted.

A tool that can handle more than one question at a time is useful. Modern LLMs handle that with ease. So it's completely reasonable to be critical of that limitation.

Sure, what’s not reasonable is expecting Siri to be a modern LLM, when they know it’s not. They asked a question they knew Siri couldn’t handle just to slam it. I’m not critical of a 5-function calculator for not one-shotting complex equations like a computer. While Siri only does one thing at a time, I trust the answer more, because it’s doing the actual math and not just guessing what the most likely answer is, lik…

It’s not unreasonable

Amazon already reworked Alexa to be backed by a LLM months ago, and they were delayed doing it.

You’re telling me that Apple isn’t capable of the same to Siri?

Re: Apple Intelligence Foundation Language Models Tech Report 2025

#176

Post by kalleboo »

devinprater wrote: post #174

Lol and yet, Google has AI image descriptions in their screen reader, TalkBack, before Apple. Apple is supposed to be the accessibility king. But with AI, they just can't, even if they obviously have access to ChatGPT which has vision capabilities. Granted, I don't know what model Google uses because tech news don't do Android Accessibility Suite APK teardowns, but it works pretty well, and fast too.

Hasn't Apple had AI image descriptions in VoiceOver for 5 years now? https://www.idropnews.com/ios-14/ios-14-adds-ai-based-voiceo...

Re: Apple Intelligence Foundation Language Models Tech Report 2025

#177

Post by zos_kia »

0x457 wrote: post #110
astrange wrote: post #81

Earlier quoted context omitted.

An issue with this is that model quality can get a lot lower when you force it into a structured form, because it's out of distribution for the model. (I'm pretty sure this is actually what drove Microsoft Sydney insane.) Reasoning models can do better at this, because they can write out a good freeform output and then do another pass to transform it.

I have this toy agent I'm writing, I always laugh that I, human, write a code that generates human-readable markdown, that I feed to llm where I ask it to produce a json, so I can parse (by code I, or it wrote) and output in a consistent human-readable form. I'm thinking about let it output freeform and then use another model to use to force that into structured.

I've found this approach brings slightly better result indeed. Let the model "think" in natural language, then translate it's conclusions to Json. (Vibe checked, not benchmarked)

Re: Apple Intelligence Foundation Language Models Tech Report 2025

#178

Post by al_borland »

stogot wrote: post #173
danhau wrote: post #168

Earlier quoted context omitted.

Why is Siri being discussed in the context of LLMs and Apple Intelligence? Have they already released Siri 2.0 or am I missing something?

The OP is making a point that Apple is behind. They might be publishing research, but it’s completely useless to the end user buying their products.

A plethora of LLMs are available on Apple platforms. If someone wants a chatbot, they can get a chatbot on Apple products. It’s not hard.

Are all Android users using Gemini exclusively? Are all Windows users only using Copilot? Where is the native Linux desktop LLM?

I really don’t understand this criticism. Would it be nice if Siri could do more, sure. Do I have tolerance for Siri to start hallucinating on simple problems it used to use real math for, no. Do I have other options to use in the meantime to get the best of both worlds, absolutely. Where is the hardship?

Re: Apple Intelligence Foundation Language Models Tech Report 2025

#179

Post by brookst »

bigyabai wrote: post #106
brookst wrote: post #96

Earlier quoted context omitted.

I mean if you throw out all contrary examples, I suppose you are left with the simple lack of nuance you want to believe

All examples contrary to what? Admitting to being muzzled by feds? Take all the space you need to lay out your contrary case. Did the San Bernadino shooter predict this?

You literally said that we should disregard this example and focus on the “real” situation as evidenced by a different example.

It is exactly the same thing as saying “if you ignore the heads, these coins really always come up tails”.

Does the Chewbacca argument method ever work these days?

Re: Apple Intelligence Foundation Language Models Tech Report 2025

#180

Post by pjmlp »

dijit wrote: post #61
simonw wrote: post #47

Earlier quoted context omitted.

One problem with Apple's approach here is that they were scraping the web for training data long before they published the details of their activities and told people how to exclude them using robots.txt

Uncharitable. Robots.txt is already the understood mechanism for getting robots to avoid scraping a website.

Assuming well behaved robots.
Post reply on HN