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

Local AI needs to be the norm

unix.foo

Post reply on HN
Print view View original

271–280 of 804 posts

Re: Local AI needs to be the norm

#271

Post by digitaltrees »

datadrivenangel wrote: post #239
reisse wrote: post #212

Earlier quoted context omitted.

> They will be, and that moment is not that far off. It's here, right now. I'm running quantized Qwen and Gemma on a decent, but three years old gaming rig (think RTX 3080 12GB and 32 GB RAM). Yes, it's slow, it has a small context window. But it can (given a proper harness) run through my trip photos and categorize them. It can OCR receipts and summarize spendings. It can answer simple questions, analyze code and ev…

In my experience once you get to ~30 gigs of ram for a model like Gemma4, the rest of the 128g of memory is simply nice to have. The speed and costs are what make it tough though, because its slower and more expensive than the same model served on a big accelerator card, and is going to be worse than a frontier model.

I wonder if it really needs to be worse. I am playing with the idea of fine tuning a model on my exact stack and coding patterns. I suspect I could get better performance by training “taste” into a model rather than breadth.

Re: Local AI needs to be the norm

#272

Post by pabs3 »

try-working wrote: post #199
oytis wrote: post #27

Earlier quoted context omitted.

What is the business model of open weight AI? I don't think there is any. At best it can serve as an advertisement for the more advanced models you sell. The huge difference to open source is that you can't just train an LLM with free time and motivation. You need lots of data and a lot of compute. I sure want to be wrong on that, I definitely like the open-weight version of the future more

Open sourcing models is a marketing strategy. Chinese labs and small international labs have no awareness or distribution, so unless they become a hot topic for a while, nobody is going to bother trying out their models. Open source gets them that, and is essentially a tax on newcomers. When you start out you simply have no other option but to open source your models. So, the business model of open models is the same…

None of these models are open source, they are just public weights, with licensing that sometimes but usually doesn't meet the Open Source Definition.

The Open Source AI Definition (OSAID) is quite ridiculous, I prefer the Debian ML policy for defining freedoms around AI.

https://salsa.debian.org/deeplearning-team/ml-policy/

Re: Local AI needs to be the norm

#273

Post by derektank »

dmd wrote: post #56
worldsayshi wrote: post #31

Earlier quoted context omitted.

It should be feasible to crowd fund training runs right?

A training run costs somewhere in the neighborhood of a billion dollars. That’s a thousand millions. How many crowdfunded projects do you know that have raised even one percent of that? Who’s going to be in charge of collecting that scale of money? Perhaps some sort of company formed for the benefit of humanity, which will promise to be a non-profit? Some sort of “Open” AI? Oh, wait.

It’s well within the capabilities of governments in developed countries. If Mistral did not already exist, I would definitely expect the French government to invest in a national LLM, if only because of how defensive they are of the French language.

Re: Local AI needs to be the norm

#274

Post by antidamage »

The roadblock to this is you seem to have to build it yourself. I've noted that none of the current cloud models are very good at building a replacement for themselves, and there's significant work that needs to be done to make a local LLM reliable in any way. I haven't found a single standalone package that makes setting them up easy. Sure, I can run Hermes Agent and a model, but getting the self-reflection loop in and all of the other stuff the need to actually be good? I'm still at it, trying to get anything to work reliably and factually.

Re: Local AI needs to be the norm

#275

Post by bytecauldron »

wmf wrote: post #95
bytecauldron wrote: post #71

Earlier quoted context omitted.

This is a bit disingenuous. People aren't losing their shit about a local model being installed. It's the lack of user autonomy. Just give the option to download a model instead of a silent install. It's not that hard. This is how every other local option works.

AFAIK Apple and MS auto-download local models.

Sorry, I should have been more specific. This is how every *good local option works.

Re: Local AI needs to be the norm

#277

Post by antidamage »

reisse wrote: post #212
pronik wrote: post #80

They will be, and that moment is not that far off. We've got the progression in place already: first, large data centers could have performant LLMs, we are now firmly in "a bunch of servers with a couple of H100s each" territory, slowly going into "128 GB VRAM on a MacBook Pro or a Strix Halo". Within the next year, the pattern of "expensive remote LLM for planning, local slow-but-faster-than-human LLM for execution"…

> They will be, and that moment is not that far off. It's here, right now. I'm running quantized Qwen and Gemma on a decent, but three years old gaming rig (think RTX 3080 12GB and 32 GB RAM). Yes, it's slow, it has a small context window. But it can (given a proper harness) run through my trip photos and categorize them. It can OCR receipts and summarize spendings. It can answer simple questions, analyze code and ev…

This is my exact setup as well and dear lord gemma is absolutely batshit insane. I'm trying to get a self-reflection and confidence loop going now, but it does feel like it's not the local resources, it's the limits of the training. Dedicated coding or dedicated real-world task models would be a good optimisation.

Re: Local AI needs to be the norm

#278

Post by beloch »

TheJCDenton wrote: post #20

For the mainstream audience, the sentiment around local ai today is the same that they had around open source a few decades ago. For a few products, some paid solutions were so much more advanced that open source were very often completely overlooked. Why bother ? And the like. Then we had captive SaaS and other plateforms and now it's obviously wrong for most of us. The dependency we have with anthropic and openai f…

Keep the Silicon Valley pattern in mind:

1. Innovate, create, and offer it all at sweetheart prices to the public while you rack up debt.

2. Shovel in more money and either buy out or outlast the competition. Become dominant. Lock in your users any which way you can.

3. Enshittify and cash in.

The deals Anthropic, OpenAI, etc. offer won't stay this good much longer. Don't let them lock you in. Failing that, you should budget more for the same service. You're going to need it. Having an open alternative running on your own hardware offers non-negligible peace of mind.

Re: Local AI needs to be the norm

#279

Post by reverius42 »

reisse wrote: post #259
winocm wrote: post #247

Earlier quoted context omitted.

Perhaps I am the odd one out here, but a small part of me wants to see what happens when you run a proprietary SOTA model on a laptop.

Nothing special? I mean, inference engine might need to get some tweaks, to support whatever compute is available. But then, if you put a few terabytes of disk for swap, and replace RAM to bigger sticks if possible, it should work? Slowly, of course, but there is no reason it should not to.

The big difference will be measuring seconds per token instead of tokens per second.

Re: Local AI needs to be the norm

#280

Post by digitaltrees »

throwyawayyyy wrote: post #191
giobox wrote: post #155

Earlier quoted context omitted.

> they don't have a used by date For quite a lot of use cases, the current systems arguably do get worse over time if not continually updated. The knowledge cutoff date will start to hurt more and more as the weights age in a hypothetical scenario where you are stuck with them forever. Coding, one of the most popular usescases today, would not be great if it say only understood java to a version from years ago etc. h…

One solution is not to advance anything of course. I'm not even joking, is there going to be a successor to React? I suspect not, with the vast amount of training data for React now, it's going to look silly to move to something else with less support. What is the last new popular programming language, rust? Will there be another one? I suspect not. Same reasoning. The irony of all this AI acceleration talk is it'll…

Yes. I am seeing a big push to use vanilla js for single file html apps that are easy to build, deploy and distribute because they have no build step. I could see component libraries emerging that make it easier build from chat interfaces with less ceremony
Post reply on HN