Conjori: Two Minds, One Channel
Books by Karl Bunch about what I found in over 2,500 sessions with large language models since January 2023. The word Conjori is coined, rooted in the Latin conjurare: to swear together, to call something into existence jointly. Two different kinds of minds, one human, one large language model, conjuring something neither could produce alone.
The dedicated site for the series is at conjori.com.
Book 1: Two Minds, One Channel
Where Human Insight and Machine Intelligence Converge. The full framework. Paperback and Kindle.
- Amazon (paperback & Kindle, ISBN 9798995789116)
- Goodreads
- Books-A-Million
Book 2: Turn Your Large Language Model Around
Learn How LLMs Really Work and How You Can Make More Effective Use of Them. The essay-length companion, about an hour to read. Kindle.
Book 3: AI Isn't What You Think It Is
The shorter, sharper companion. Kindle.
Why this book
The quote on the front page of this site has been there since 2014: "Every computer language is an imperfect way of describing a potential solution to a poorly understood problem."
I wrote that down because it captured something I had felt for decades but never articulated. The crucial phrase is "poorly understood problem." The whole industry defaults to encoding solutions before the problem has been adequately explored. I noticed the same trend happening with AI tools.
What most people call "AI" is a marketing term that obscures something more interesting: a system that reverse-engineered the way humans have been compressing what they know into language for 100,000 years. Not artificial intelligence. Disembodied intelligence. Fluent in the one medium we share, blind to the experience that medium was built to carry.
Understanding that distinction, and understanding what you bring to the connection that no machine can replicate, changes everything about how you use these tools.
For the origin story, see the launch post.