Early adopters get to play with an early version of integrating a large language model into your Hub

Earlier this week I used an excerpt from a chat with Philip Weiss & Jesús Azogue as a starting point for a conversation with ChatGPT about some of the content in my Hub.

"If Charts lie, ChatGPT visualisations lie brilliantly". Exploring knowledge visualisations powered by ChatGPT, which can be particularly problematic because of the way the LLM's hallucinations - already hard to spot by their very nature - are also hidden behind the visualisation. But they have real potential as a creative muse.

My first experiment with a GPT built on my previous 5 experiments into integrating MyHub.ai with ChatGPT.

"a modern version of del.icio.us meets Roam... a searchable, interconnected repository of the most insightful content on the Internet" - and a pretty interesting example of convergent evolution vis a vis myhub.ai

This piece captures and then explores exactly what I've always thought about the future direction of myhub.ai: imagine what would happen if you had your own personal AI assistant operating across your content - your public posts, private library (including content shared from friends, stuff in your reading queue, etc.) and the wider web, emph…

Covers "a new class of apps called “Integrated Thinking Environments (ITEs)”... [and] NOTE framework, used to describe the specific feature sets ITEs provide... examples and some future directions".The term ITE riffs off "Integrated Development Environments... provide developers a comprehensive set of tools ... a kind of augmented c…

The chatbot you can find on my example Hub is a pale imitation of what Beta users should get.

While the AI engine will be the major development, other ideas include disinfo analyses, filter bubble breakers, social features, chatbots...