Welcome to the MyHub.ai "Experiments wiki"

I'm working with the garage door up as I learn how best to integrate AI with MyHub.ai.

Integrating MyHub.ai with an LLM has been the idea from the outset (the hint's in the ".ai"), with the longterm goal being "creating a decentralised, open-source ecosystem ... developing cooperatively-owned AI engines to benefit society as a whole" (How Artificial Intelligence will finance Collective Intelligence).

But as anyone who has played with any LLM for any length of time knows, getting the best out of them is not easy. You need to try stuff out, compare results and try some more. You need, in other words, to experiment.

The quickest way for me to experiment with integrating an LLM into MyHub.ai is to turn it into a ChatGPT wrapper, so over the summer we added a pilot version of ChatGPT integration to support the research (see pilot MyHub ChatGPT integration).

As the MyHub,ai Early Adopters will soon get to play with this AI-boosted version of MyHub.ai for free for a month or three, I thought I'd share my research as I go. Given that I am managing my research notes in Obsidian, sharing them here via a massive wiki was the obvious solution (read more about this massive wiki).

Starting points

Integrating MyHub.ai with Large Language Models

  • Today: How to chat with ChatGPT about your content (v2) explains how MyHub/ChatGPT currently works.
    • If you're an Early Adopter kicking the tyres, this is a good place to start
    • Do you have your own ChatGPT API key and a Hub? Email me and I'll set this up for you
  • Tomorrow: How (do I currently imagine) will the LLM integration into MyHub.ai look like in future? See chatgpt integration plans

Research

Learn more