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

Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

gizmoweek.com

Post reply on HN
Print view View original

111–120 of 196 posts

Re: Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

#111

Post by goodmythical »

HarHarVeryFunny wrote: post #93
devmor wrote: post #62

Earlier quoted context omitted.

AI detectors that use text as a basis are not real. It is fundamentally impossible for them to exist.

Huh? LLM output doesn't have the variety of human output, since they operate in fixed fashion - statistical inference followed by formulaic sampling. Additionally, the statistics used by LLMs are going be be similar across different LLMs since at scale its just "the statistics of the internet". Human output has much more variety, partly because we're individuals with our own reading/writing histories (which we're dra…

[dead]

Re: Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

#112

Post by tsycho »

rich_sasha wrote: post #108

Offline or not, I'm sure Google uploads every keystroke, phone orientation, photo, WiFi endpoints and your shoe size when you interact with it. To enhance your experience.

> ...your shoe size

The funny thing is that a lot of Google's internal training content uses an imaginary product "gShoe", and discusses the privacy implications of data that such a shoe might collect :D

Re: Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

#113

Post by ben_w »

HarHarVeryFunny wrote: post #93
devmor wrote: post #62

Earlier quoted context omitted.

AI detectors that use text as a basis are not real. It is fundamentally impossible for them to exist.

Huh? LLM output doesn't have the variety of human output, since they operate in fixed fashion - statistical inference followed by formulaic sampling. Additionally, the statistics used by LLMs are going be be similar across different LLMs since at scale its just "the statistics of the internet". Human output has much more variety, partly because we're individuals with our own reading/writing histories (which we're dra…

> LLM output doesn't have the variety of human output, since they operate in fixed fashion - statistical inference followed by formulaic sampling.

This is the wrong thing to look at; your chess analogy is much stronger, the detection method similar (if you can figure out a prompt that generates something close to the content, it almost certainly isn't human origin).

But to why the thing I'm quoting doesn't work: If you took, say, web comic author Darren Gav Bleuel, put him in a sci-fi mass duplication incident make 950 million of him, and had them all talking and writing all over the internet, people would very quickly learn to recognise the style, which would have very little variety because they'd all be forks of the same person.

Indeed, LLMs are very good at presenting other styles than their defaults, better at this than most humans, and what gives away LLMs is that (1) very few people bother to ask them to act other than their defaults, and (2) all the different models, being trained in similar ways on similar data with similar architectures, are inherently similar to each other.

Re: Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

#114

Post by altruios »

temp7000 wrote: post #45

Is it me, or does the article sound like LLM output? The pattern "It's not mere X — it's Y", occurs like 4 times in the text :v

It is like the AI is training us to avoid certain language patterns. I rebel at the hostage of weak language: for strong language is next.

Re: Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

#116

Post by veunes »

I noticed the inference is routed through the gpu rather than the Apple neural engine. Google’s engineers likely gave up on trying to compile custom attention kernels for Apple’s proprietary tensor blocks iirc. While Metal is predictable and easy to port to, it drains the battery way faster than a dedicated NPU. Until they rewrite the backend for the ANE, this is just a flashy tech demo rather than a production-ready tool

Re: Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

#117

Post by declan_roberts »

rich_sasha wrote: post #108

Offline or not, I'm sure Google uploads every keystroke, phone orientation, photo, WiFi endpoints and your shoe size when you interact with it. To enhance your experience.

Apple is paying Google $1billion for an AI strategy that runs on device. We're seeing the preview of what that will look like.

Re: Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

#118

Post by veunes »

BeetleB wrote: post #98
temp7000 wrote: post #45

Is it me, or does the article sound like LLM output? The pattern "It's not mere X — it's Y", occurs like 4 times in the text :v

I don't care if it's written by an LLM. The problem with the article is the complete lack of details. No benchmarks on the iPhone capable models. No details, whatsoever. Human or LLM - the article is a whole lot of nothing.

This article is all fluff because real benne marketing. If they mentioned that a 4B model on an iPhone 16 drains 15% of the battery for a single long prompt and triggers hard thermal throttling after 20 seconds, nobody would be clicking on headlines about "commercial viability" fwiw

Re: Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

#119

Post by lynndotpy »

mtremsal wrote: post #51
temp7000 wrote: post #45

Is it me, or does the article sound like LLM output? The pattern "It's not mere X — it's Y", occurs like 4 times in the text :v

An AI slop pattern so widespread it’s now referred to as “it’s not pee pee it’s poo poo”.

It's not just a widespread pattern –––––––––––––––– it's a sign of things to come.

Re: Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference

#120

Post by codybontecou »

CubsFan1060 wrote: post #31
codybontecou wrote: post #11

Unfortunately Apple appears to be blocking the use of these llms within apps on their app store. I've been trying to ship an app that contains local llms and have hit a brick wall with issue 2.5.2

Though of course Apple's rules aren't always consistent, I have 2 separate apps currently on my phone that can/are running this (Google's Edge Gallery and Locally AI)

They've been slowly cutting them off of updates and/or taking them off the app store entirely.

See Anywhere and Replit. Anywhere was the #1 or #2 app and was taken off the app store entirely before being put on and then taken off again.

Last I checked, Replit hasn't received an update on the iOS app store in over two months due to reviews denying them.

Post reply on HN