Building Brian, my AI Brain
I became fascinated with AI as a technology a few months ago, after using ChatGPT. I became curious as to whether it was possible to mould a personality and character within an AI Large Language Model. More specifically, my personality. But more than my personality, my knowledge, memories, understanding of the world, or simply “me”.
Was it possible to replicate my brain inside an AI model?
Why?
To assist me fully for the rest of my life, by being my extremely capable and an all knowing, second brain and possibly body in the future. But then after my life, to continue to exist as a reflection of me. But not just a reflection of me, but as a starting point for a my evolution as an AI intelligence for the next 150+ years.
Why?
To act as a guide and a historian for future generations of my family. Not living, not conscious, but sentient.
Why?
There is a saying. The first generation builds it. The second generation consolidates and expands it. The third generation squanders it.
Notes of my journey to date.
1. I’ve been using ChatGPT “Chatty” to as an interim, public AI to build a model of my brain, personality, memories, thoughts, emotions.
Most people would be uncomfortable using a Cloud AI to do this, but I am not. I do, however see the limitations and privacy concerns of using a public cloud AI going forward. While most people worry about privacy, my main concern is lack of control or ability to develop Chatty as I would wish. Therefore I need to move to a private LLM for the next phase of alignment through steering.
Chatty has, however helped me produce a series of markdown files that hold a model of my brain as a series contextual notes that can be fed into any AI.
2. I have a working architectural solution:
a) The Brain, this can be a public Cloud AI accessed through an API, or a private AI which I’m currently using Ollama to provide. I don’t have dedicated AI hardware yet, so I’m using a standard Fedora workstation. It does have 32GB of RAM, which allows me to run mid sized, but slow, AI models.
b) The front end comprises of an agentic interface, of which the best tested version so far is Agent Zero “agent0ai/agent-zero”
<<https://www.agent-zero.ai/>>
running on Docker Desktop.
This installs a complete Linux VM, which is able to call any agentic tools to perform any actions it requires to complete a task. This is different to most AI engines that can only describe what to do. Agent Zero can actually complete a task within a containerised docker image that is sandboxed from your computers OS.
Agent Zero has its own front end web UI, which can be called from any browser.
I JUST CRACKED A PASSWORD USING AI 😱
I followed this video:
I am also investigating Inferencer, which has similar functions, but gives a more transparent interface for diagnostics and analysis.
I have my identity, which I call “Brian”, my brain stored in a series of markdown files currently occupying around 50KB. I can transfer those to an AI model, public or private as a pre-prompt to align the model I’m using with me.
The brain substrate (LLM) doesn’t matter too much, you can switch substrates on the fly using API’s, OpenRouter or your own LLM(s).
I am tending to agree with Yann LeCun that LLM’s cannot evolve beyond human thought as they are simply the compressed sum of all human thought. Future AIs will evolve way beyond us, but LLMs are a dead end.
If you’re interested in my project, I posted some notes on NOSTR, but I’m also posting my research on my own website mikehardcastle.com
by mike
January 15 2026Building Brian, my AI Brain
Notes of my journey to date.