Hacker News

Today, not much differentiates them. But as time passes our only option will be to further specialize the hardware to get realistic gains; at some point perhaps a 'purpose built analog' computer kinda thing will get to the point where it is so useful, that it would be like the 'Standard Template Constructs' concept in Warhammer 30k. So what you can make a faster ai but, the current one can 'teach everyone, basically anything'.

That first bullet is a bit sketchy. Benchmarks, particularly geekbench, may have increased 6x, but that's being manipulated.

The GPUs have become much larger, so 6.8x is believable there, as is the inclusion of a matmul unit boosting AI.

The 2.x numbers are the most realistic, especially because they represent actual workloads.

You’re kindof undermining your own point. Ten years later the only thing you’d need to upgrade for your home server might be the GPU - because a new use-case emerged. Okay? Spend $500-$1000 on an eGPU. Problem solved. Will that eGPU setup last another ten years? If all it’s doing is processing security video and routing claw-like tasks, then yes.

It really just depends on if the hardware is "good enough" for whatever its purpose is. If the hardware today can locally run whatever models for your security cameras, it's likely they will still be "good enough" in 10 years.

Of course, similar to a 10 year old car or appliance, you will be missing any new features or bells and whistles that have become available in the meantime.

Decades is a long time for hardware, but "years" seems reasonable soon. The commercial models are "good enough" for a lot of things now, so if that performance makes its way into the on-device space for "home applicance"-level cost (<$5k at the start, basically), I'd expect a lot of stuff to start popping up there. In offices too.

Like the PC in the 80s starting to eat up "get a mainframe" or "rent time on a mainframe" uses.

Yeah but, how long do mainframes last? Think of the COBOL systems used in government. No reason to update them, they worked forever; their job is discrete and they performed it well enough where intense updating wasn't a requirement.

I think that attitude is (very) slowly changing though and might not be the default forever.

My elderly parents have asked me about "local backups" of their cloud stuff, their Facebook history etc..

If they're thinking about the risks/tradeoffs of being in the cloud..

I think people use the cloud because there's no better/easier option today.

But at some point there might be. A home appliance (which may be similar to a homelab under the hood but the user experience is where things change) that provides a bunch of automation and home services could be quite attractive if it got to a point of being very turnkey for the average family.

Just like a TV or a gaming console is today.

I'm thinking 'everyone needs an air conditioner', kinda need. Instead of 'some nerds run servers'. And this 'ac' is your 'ai'.

Maybe even subsidized by the government. This will be a fundamental need.

Strongly agree. Plus, for all but very specific usecases, most people will spend less money by paying for cloud services, with "most" here referring to the general population.

Home labs feel wholly different and requires custom setup and maintenance.

A home appliance like a toaster would be in the case of an AI server are ready to go appliance that’s preloaded and confined and connect to everything in your home and help you manage it likely by just voice chat or some amount of interface.

Perhaps if we truly run out of steam on the process node front?

There's potential case for a subscription model to keep security updated for the connection to the users' phones as well as on going support for less tech savvy users (e.g. "I told my assistant to turn on my smart dishwasher and it turned on the my smart washing machine instead"). I'd imagine the HN crowd would lean toward a open source version though.

With that logic, there wouldn't be anyone selling refrigerators or dishwashers.

Well, custom/bespoke training for your families particular needs perhaps, performed once every 5 years.

I mean I envision analog/custom/bespoke ai hardware that is fundamentally 'good enough'. I mean as the market increases its need for these systems and as time progresses at some point it'll like warhammer 30k where these 'standard template constructs' are smart enough to basically teach you anything.

I really think this is a temporary scenario, there will be advancements in ai's building the next generation of ais, where the scale of the model continually shrinks and maybe there will be some break through that allows us to double the use of existing hardware/memory etc.

10 years ago I couldn't do alexa at my house, now I'm pretty close with a Qwen3:8b / Ollamma LLM (I mean I never really wanted alexa to do anything other then play music, automate stuff, etc. zero interest in it teaching me how to code).

I'm even thinking at some point we'll consider ai to be a fundamental human right to have access too as otherwise you are inherently in a disadvantaged position in terms of wealth prospects to those who do have access.

This picture of the Ryzen AI Max+ blew my mind.

https://images.prismic.io/frameworkmarketplace/Z7aVJZ7c43Q3f...

Look this isn't an ad. I've been building my own desktops since I was 14. It's always been a CPU and motherboard and memory separate type of deal but this thing has it all integrated. Look how small it is. I use Gentoo. I compile all the things. I know exactly how long it takes to compile gcc because I do it all the time.

This thing compiles the linux kernel in 62 seconds. And it uses less power than my current machine to do it. I am jealous. The computer age is not slowing down. It's in fact speeding up. Am I the only one excited as fuck about what's coming?

You don't even need a GPU because it handles gaming tasks like it's nothing.

If "small models" is the bar, then you can run inference for ~$50 on Raspberry Pi like hardware. I do that with 1.8b-4b models.

Perhaps OP was referring to a usable agentic system, for which $2500 sounds about right.

I've got a 3060 myself, which is nice to play around with the smaller models for free (minus electricity) and with 100% uptime, but I was not able to program anything with them yet that I didn't want to rewrite completely. A heavily quantized Qwen3.5-27B model is getting close though. Maybe in a few months.

For coding and personal assistance the context window on 16GB is not good enough. Ideally I want a context window of 100k.

I already run frigate. I am asking how this stacks up to it.

Before anyone buys a TPU for Frigate, try OpenVino on a cheap Intel N100 CPU. My mini PC frigate installation can handle 5 cameras easily.

Depending on the age of your hardware, you might already have something more powerful

Are we “there” yet? To the point where deploying this as a serious security system makes sense? Or are we still in the research and demo phase?

My intuition is that OpenClaw-like systems still make too many mistakes to be trusted with security. And that it will take more months or years until the models and harnesses are truly ready.

Or you come home from that Juggalo reunion concert:

https://news.ycombinator.com/item?id=47438675

Edit: and while the parent comment and this are made in at least part jest, the discovery of bugs and emergence of adversarial and secondary uses will be interesting.

For example, imagine being able to run gait analysis for neurological disorders against yourself from your own security cameras.

Not necessarily. But fixed code tends to not adapt to changing situations.

“Hey, my mother-in-law is coming today. She drives a blue Ford pickup. Let her in and record the car plate for future use.”

“There are servicemen coming today around noon. They should check the electricity box and leave in a few minutes. Let me know if they do something else.”

Yes you can get an RTSPS stream, but looks like Aegis is doing some validation that won't accept them. They look like - rtsps://192.168.1.1:7441/uOndh6hJd3Bti4kd?enableSrtp

Context is your limitation, on the M5. The larger your model is, the longer you'll be waiting on token prefill. TFTT with 0 tokens of context isn't a real-world benchmark.

That's why most professional inference solutions reach for GPU-heavy hardware like the Jetson. Apple Silicon seems like a strange and overly expensive fit for this use cae.

I've been doing a lot of experimentation with Qwen3.5 models locally, and I've found for other tasks that the Opus 4.6 distilled versions of the model ("Qwopus") tend to perform better for other tasks. But this is mostly based on the quality of output, not necessarily from a performance perspective. I'll report back once I get around to running the benchmark. I'm also interested in applying local AI tools onto my local security setup (built on UniFi).