01 Light: a voice interface for your home computer | Hacker News Reader

01 Light: a voice interface for your home computer

openinterpreter.com

22 pointsdavidbarker5 comments

This is very cool and the demo is exciting...but I still don't know what this actually is.

From the repo[0] they refer to it as an operating system, but in all the install instructions and code it appears to be a program that still needs an OS to run, although I'm not clear what the requirements are. The demo makes it appear as if it were an LLM powered program that can interface with an existing OS, or is the actual product the voice device?

0. https://github.com/OpenInterpreter/01

The idea is to use a voice interface to actually perform "skills", like Alexa. Check out the prompt and you can get an idea of how they've set it up. So the LLM generates code that can then be executed to perform actions.

https://github.com/OpenInterpreter/01/blob/main/software/sou...

There don't seem to be many skills defined in this repo though, but I didn't look too hard. This software is the server, and then they have a small remote device that can talk to the server and it appears to use ngrok for that.

[replying to comment here]

I totallly agree that the term "OS" is used for a lot of projects that are not actually what I would call an OS. My own employer is guilty of this. :) Yes, this seems to be just like UFO, and Rabbit, and other similar projects.

Right, but that's not an OS, that's a software application run by the OS like Microsoft's UFO[0]. The ability to "teach" the LLM by converting your teachings to those skills is very clever though.

0. https://github.com/microsoft/ufo

From what I gather, this project started out as an implementation of a code-interpreter using a local LLM. Basically your instructions are used to write code by the LLM, which is then executed. The idea is that it can be much more powerful having access to your native systems shell instead of only sandboxed python.

In the meantime, it seems that also models with vision capability have been added, that can be used to access GUI based applications, not only the shell.

It's a very exciting concept that lives in a space where open source software should have a significant advantage due to its transparency. (Or would you give a black box device access to everything on your computer?).

It also seems to one of several emerging projects that try to sketch out a path for ideas of how LLMs could change the way we interact with computers.

Has anyone found any basic specs (e.g. around battery life) for the 01 Light device?

Reply on news.ycombinator.com