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

171–180 of 196 posts

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

#171

Post by HarHarVeryFunny »

ben_w wrote: post #113
HarHarVeryFunny wrote: post #93

Earlier quoted context omitted.

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 y…

An LLM is just computer function that predicts next word based on the input you give it. It doesn't make any difference what the input is (e.g. please respond in style X) - the function doesn't change, and the statistical signature of how it works will still be there.

If you don't believe me, try it for yourself. Ask an AI to generate some text and give it to the AI detector below (paste your text, then click on scan). Now ask the AI to generate in a different style and see if it causes the detector to fail.

https://app.gptzero.me/

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

#172

Post by cyanydeez »

Forgeties79 wrote: post #163
bigyabai wrote: post #150

Earlier quoted context omitted.

> No amount of bloat matches what an LLM needs. I don't think that's necessarily true. For instance, LinkedIn uses more memory than Gemma E2B inference does.

LinkedIn is an entirely different category and an extreme case at that. We’re not talking about LLM’s replacing LinkedIn either. It’s an entirely different comparison/discussion.

Finally, we've fully documented the Singularity-is-actually-just-bloated software.

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

#173

Post by andrewblossom »

the_pwner224 wrote: post #148
satvikpendem wrote: post #145

Earlier quoted context omitted.

Edge Gallery does have NPU support, it needs you to install the beta of AICore on the Play Store, the Edge Gallery app has instructions.

Huh I didn't see those instructions when I tried it last week. Must not have looked closely enough. I do remember it not having NPU support (confirmed by other people) back at the Gemma 3 launch a while ago.

It won't even let you try Gemma4 until you install a beta update to AICore as of today.

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

#174

Post by newsoftheday »

js8 wrote: post #161
newsoftheday wrote: post #132

Earlier quoted context omitted.

What if the prompt includes, "Produce output that doesn't sound like an AI generated it."?

I got curious and tried: https://claude.ai/share/3af7bd6a-15f8-4533-9dc3-a44adef255b3

That's actually interesting, thanks. It's like AI is tattling on itself.

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

#175

Post by devmor »

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…

A human can easily produce output that looks like anything an LLM can produce, therefor an LLM detector that can say "this is 100% written by AI" cannot exist. It's really that simple.

> Can you ever be 100% sure? Maybe not

The commenter I was replying to claimed exactly this. Their AI detector showed that the text was "100%" AI generated.

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

#176

Post by fancyfredbot »

juancn wrote: post #138

Gemma4 is still power hungry since it tends to activate pretty much every weight. qwen3-coder-next uses a lot less since it seems to only activate ~3B parameters at a time. My guess is that this is still close to tech demo, and a lot of performance is left on the table.

The article is about two models which have either 2B or 4B parameters. Both are dense models. The 2B version will certainly use less power than qwen3-coder-next.

The models are quite good. They aren't just a tech demo.

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

#177

Post by HarHarVeryFunny »

devmor wrote: post #175
HarHarVeryFunny wrote: post #93

Earlier quoted context omitted.

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…

A human can easily produce output that looks like anything an LLM can produce, therefor an LLM detector that can say "this is 100% written by AI" cannot exist. It's really that simple. > Can you ever be 100% sure? Maybe not The commenter I was replying to claimed exactly this. Their AI detector showed that the text was "100%" AI generated.

I was just expressing some caution. Saying you are 100% certain of anything when the evidence is statistical seems a bit too certain, especially if it was just from a short text sample.

Compare to flipping a coin, counting heads vs tails, and trying to assess if it's a fair or biased coin. After 1000 flips if it's not close to 50/50 you would rightfully be suspect, and if it was 10/90 you should be almost certain it's biased. But you can never be 100% sure.

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

#178

Post by marvin-hansen »

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

I disagree. My iphone app ships with an ANE optimized LLM that runs fully offline. Sailed straight through the App Store review same day after only one minor correction. It could be possible that Apple gives apps that use LLMs for it's core functionality a pass as long as it has nothing to do with vibe coding. The recent removal of the the Anything Vibe code app supports the thesis that Apple wants to prevent a flood of Ai slop apps; at least in theory as Apple can't block people from building with Claude Code & Co.

https://www.macrumors.com/2026/03/30/apple-pulls-vibe-coding...

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

#179

Post by ben_w »

HarHarVeryFunny wrote: post #171
ben_w wrote: post #113

Earlier quoted context omitted.

> 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 y…

An LLM is just computer function that predicts next word based on the input you give it. It doesn't make any difference what the input is (e.g. please respond in style X) - the function doesn't change, and the statistical signature of how it works will still be there. If you don't believe me, try it for yourself. Ask an AI to generate some text and give it to the AI detector below (paste your text, then click on scan…

I can't use that linked app, paywall immediately. Unlike the person you were replying to here[0], I do not claim that this is impossible:

LLM is indeed just computer function that does stats. And our brains are just electro-chemistry that does stats. This is why stylometric analysis of human writing is a thing.

My previous experience with things such as you have linked to, is they used to be quite poor. I assume they're better since then, but then again so are the models.

[0] https://news.ycombinator.com/item?id=47778171

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

#180

Post by ben_w »

js8 wrote: post #161
newsoftheday wrote: post #132

Earlier quoted context omitted.

What if the prompt includes, "Produce output that doesn't sound like an AI generated it."?

I got curious and tried: https://claude.ai/share/3af7bd6a-15f8-4533-9dc3-a44adef255b3

Basically the same on ChatGPT. DeepSeek managed to generate output rather than meta-discussion about how to generate output.
Post reply on HN