You know, I've always liked Futurama but I always kind of thought it was silly that literally everything has an AI and a personality.
But, you know, I actually think that there might be a logic to it. Economies of scale might mean that almost-literally every computer you buy in the year 3000 has some kind of AI-assistance chip in there, and sure maybe it will have full AI with a personality spitting out one-liners.
I'm curious how this would handle grammar checking on a basic word processor. Or maybe generate worlds for small text based games. I have no idea what the capabilities are of a cluster like this.
12 comments:
haha … this is precisely the kind of project that https://bil-lang.org is aimed at: Go for parallel (ie in this case pipeline processing).
don’t get too excited until we get the TinyGo backend built though ;-)
Soon ai in every lightbulb running Kubernetes
Praise the Omnissiah.
You know, I've always liked Futurama but I always kind of thought it was silly that literally everything has an AI and a personality.
But, you know, I actually think that there might be a logic to it. Economies of scale might mean that almost-literally every computer you buy in the year 3000 has some kind of AI-assistance chip in there, and sure maybe it will have full AI with a personality spitting out one-liners.
Change the year 3000 to the 2030s and it might be just as accurate.
Kind of like how disposable vape pens often have a 24 MHz Cortex-M0+ with 3 kB SRAM and 24 kB flash, which would have seemed ludicrous a while back.
I'm curious how this would handle grammar checking on a basic word processor. Or maybe generate worlds for small text based games. I have no idea what the capabilities are of a cluster like this.
It is a bit of a bummer to see that the degree of 'compression' makes it a fancy llm noise-maker. It is still charming.
I’m actually working on a small project that’s exactly this! Less quant so it’s only 150M parameters but this is amazing.
Thanks for sharing. It's fascinating to see a 0.5B LLM being split across seven ESP32s like this.
Gemma 4 when?
We're gonna need a bigger ESP.