Hacker News Reader

Comment by jconley | Hacker News Reader

This is a cool project. One of my pet ideas that I haven't done is to build a home assistant where all data is stored and processed by a home "server". The biggest benefit I see is that it could truly be omnipresent. There in the background, answering questions, jumping into your conversations without prompt. And it's much less creepy if all that data isn't going to someone else's computer.

Also piping in and processing the data from my mobile would be cool, but I wouldn't want to invade other people's privacy if I'm in public.

View on HN

SAID this before physical VPN and open source cloud is exactly what Im trying to make a reality VM to the TVs not to mention we all need that Hillary Clinton privilege AS WELL as when you pull in at home you car uploads. updates, charges (manuel plug for now) and tie that in to the obd reader software that alone could invaluable also having two devices is the best solution one staying the car gives me a internet connection to my car for remote access does my maps or music the other does my Hud

It does not sound like a realistic capacity plan. The reason this works in the cloud is the inference can be run in parallel on a huge amount of hardware for a short time. To run those kind of models on your rinkydink computer would take forever.

Respectfully, I don't think that's true. "The Cloud" is just computers in a warehouse somewhere

$5/month's worth of "cloud" is going to work out to be less actual raw CPU resources than a low end raspberry pi running full time in-house

I don't actually think they're true.

One second of Google cloud TPU has roughly the same number of floating point operations then 4 hours of raspberry pi 4B time.

So 3 minutes of cloud TPU time already covers your whole month of raspberry pi usage. Pretty sure it costs them less than 5$ as well, since they have the hardware anyways.

I don’t think a $5 instance is enough for ML/AI workloads. You need something with a GPU.

"The cloud" is also massively parallel software. If I run a Google search, many thousands of CPUs will be brought to bear on my query, and a gazillion DIMMs, and all the throughput of a hell of a lot of SSDs, and so on. If you just happened to have a copy of the web, and an index of it, on "a computer" no matter how big, it would be impossible to get prompt answers.

If Google (or whomever) needs to run voice models, they take your query and all the other queries that arrive in the same millisecond, smoosh them all together and shove the batch into a TPU and run it. You don't have any TPUs and you also don't have any traffic you can use to amortize the cost of your infrequent queries.

The idea that you could run these kinds of ML inference tasks is economically fanciful. You would need a huge investment in hardware and the opex would be ridiculous.

> The idea that you could run these kinds of ML inference tasks is economically fanciful. You would need a huge investment in hardware and the opex would be ridiculous.

Google, Apple, Amazon and even Sonos are all releasing voice assistants that work locally on their relatively low powered speakers.

Apple seems to be ahead with what is local, while Google seems to be the smartest. (Sonos doesn’t have a cloud, but it’s not ‘general purpose’ afaik).

Sure you can’t amortize them across a bunch of TPUs BUT instead they can ship custom hardware. A tpu needs to be big and support parallel streams. A home server may only need to ever serve one stream. There are arduino style devices that can perform basic tensor flow audio models in real time now. And obviously most phones can perform this locally now, so depending on opinion that may be considered affordable.

An Nvidia 3090 GPU can run open ai's whisper at 17x realtime[0]. they're not exactly cheap (~$500?), but they're cheap enough that running the transcription end at home is quite feasible. And, it includes translation, so you don't have to do it in English.

Searching all of a downloaded copy of Wikipedia wouldn't be that computationally expensive either if the assistant has hot words it picks up to look up.

[0] https://news.ycombinator.com/item?id=32928207

It's also possible to use local AI processing chips like Coral or Gyrfalcon for this.

Could just load up a pcie card full of them if necessary. A local home AI would be such a boon to people, not just the average person but the elderly as well, combined with a refined GPT etc it could conversationally respond to requests rather than most assistants' current request->response "I am a robot" scheme.

>Your son called when you were asleep to ask if you wanted to get coffee today, shall I call him back for you or put you through to him? >X, you've fallen! Please let me know you're okay or I will call emergency services for you

It's sad that we have the technology to do this already but haven't.

this is also one of my pet ideas, but I keep procrastinating. Have your idea transformed into any kind of repos that we can contribute to?

> One of my pet ideas that *I haven't done*

I suspect OP was clear enough.

But there exists https://mycroft.ai/

https://github.com/MycroftAI

Reply on news.ycombinator.com