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.

Adding an LLM to MyHub.ai 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 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 to experiment with integrating an LLM into MyHub.ai was to integrate ChatGPT with it and let MyHub.ai Early Adopters play with it (see ChatGPT integration free trial, Bullshit, Botshit and Bubbles), so I thought I'd share my research as I go. And given that I manage 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 a MyHub Early Adopter, this is a good place to start
  • Note: if you have your own ChatGPT API key you'll be able to chat with ChatGPT about your content without limits.
• Tomorrow: How (do I currently imagine) will the LLM integration into MyHub.ai look like in future? See LLM integration plans

Research

• experiment log: the actual experiments
• experimental methods: how I'm carrying out this research
• The various agent prompts and gpts and summarisers in summary used in the experiments
• Ideas log where I drop ideas for future experiments and blog posts as I go.

Learn more

• about this massive wiki
• About me and get in touch.