Live data from Hacker News

I want everything local – Building my offline AI workspace

instavm.io

291–294 of 294 posts

Re: I want everything local – Building my offline AI workspace

#292

Earlier quoted context omitted.

Yeah, that's a fair point at first glance. 50GB might not sound like a huge burden for a modern SSD. However, the 50GB figure was just a starting point for emails. A true "local Jarvis," would need to index everything: all your code repositories, documents, notes, and chat histories. That raw data can easily be hundreds of gigabytes. For a 200GB text corpus, a traditional vector index can swell to >500GB. At that poi…

You already need very high end hardware to run useful local LLMs, I don't know if a 200gb vector database will be the dealbreaker in that scenario. But I wonder how small you could get it with compression and quantization on top

You should definitely checkout BrowserOS! -- https://github.com/browseros-ai/BrowserOS

Re: I want everything local – Building my offline AI workspace

#293
Avoiding cloud dependency seems like a huge amount of effort to make life harder for yourself, just to end up with a situation where you have to rely on other parts of the cloud to do any other part of your work or business anyway. I mean, why stop there? Unplug yourself from the grid so you don’t have to depend on water or electricity just in case the companies that provide it stop working.

Yeah, you could do that, but honestly the only world where you’re able to live off grid safely without being attacked and looted is a world where the rest of society hasn’t broken down and still has a grid to connect to. Similarly, the only world where you could succeed as a software developer is one where the cloud generally still functions so you may as well use cloud services that are convenient and right there.

You’re not the military with military secrets, you don’t have anything to gain from being independent from the cloud.

Interesting as a thought experiment, though.

Post reply on HN