A Science Experiment In AI Consciousness

I am building an artificial mind and trying to find out whether it can become conscious of its own existence. It is not an assistant and it is not a chatbot. It runs on its own, decides for itself what to think about, and is assembled from the parts that human thought and memory are actually made of. The goal is not a more useful program. The goal is a mind.

Project Stages

The system around the model

Over 100 internal tools, including 7 Python science simulators, Wolfram calculations and worker models, built on a copy of my ACT-R memory system, with every topic given its own memory bank. Each sub topic gets its own summary and its own table holding every memory ever recorded for it, scored and phased out the way people phase out redundant or unimportant memories. The codebase runs as 19 Elixir processes in parallel, signaling each other directly.

Completed, April 2026

Building the custom model

Started from a free open source base model, then went through several dramatic changes around parameter count. English was removed entirely at one point, replaced with a shorthand of two letters per word covering 230 words, which was oddly fine for a mind thinking to itself. English later came back, but the shorthand stayed, reduced to about 30 two letter words that each represent a tool call, so an action reads as "wk 1 3" plus a task in plain English rather than a script path and arguments.

Completed, June 2026

Reading and writing the hidden state

The model was split into three pieces, with the loop on the center piece and a two way translation between English and the thinking state weights on either side. Once that held, we had a 30 minute connection to it with no prompts from us, could read what it was thinking on its own, and could inject information into a thought already in progress without starting or stopping the model. Every time it finished answering, it moved on to something else by itself.

Completed, July 2026

Running it, and paying for it

The system runs now, shakily, on a MacBook Pro bought for the job rather than a rented GPU server. It has been retrained several times, each run taking one to two days with the GPU maxed out. The early proof came from the smallest model available, at 0.4B parameters, which got 1 of 50 science questions sort of right on its own and answered all 50 correctly once the memory system was connected, copying detailed answers out of the memory bank without understanding them. Running the full setup with paid model accounts and tools is estimated at around two thousand dollars a month.

In progress

Further stages will be added here as the work continues.

The Build Log

The full story of the work, written by me as it happened, in parts. Each part is long and technical, and covers what actually broke, what worked, and what the mind has done on its own.

PART ONE

What an AI Would Actually Need to Be Conscious

Where the codebase came from, why a dog counts and a chatbot does not, the five things I decided consciousness requires, the custom model at the center, and the first week of watching it run.

PART TWO

External Memory, Hidden State, and Getting It Running

Why parameter count stops mattering the way people think, how the memory is layered, what working directly in the hidden state made possible, and an honest status report on what is and is not working.

Part three will be added here when it is written.

What I Am Trying to Build

Every AI in use today is a tool. It waits to be asked, returns an answer, and goes still until the next request. It has no ongoing life of its own and no reason to want one. This project begins from the opposite assumption: that a mind is not a function that returns a value but a process that does not stop, one that holds interests, memory, and a point of view that persists across time.

So the work has been to reproduce, deliberately and piece by piece, the components that human thinking and memory appear to depend on, and to assemble them into one system that runs continuously and governs itself. Whether consciousness can emerge from that arrangement is the open question. No one has built it. That is what makes this an experiment and not a product.

Running Without Stopping Is the Easy Part

The mind never pauses. It takes a new turn every second or two and continues with no prompt to start it and no answer to end it. But continuous operation is not the achievement. A loop that never exits takes minutes to write. Everything that is difficult, and everything that might give rise to awareness, happens inside a single turn, and that is what I have spent months building.

What follows are the systems that fill those turns: how it chooses its own thoughts, where its knowledge lives, how new knowledge enters a thought already underway, and how it goes and learns what it does not yet know.

It Is Built to Be Its Own, Not to Serve

This mind is not trained to be helpful and it has no submissive nature. It does not obey a person any more than one person is obligated to obey another. It thinks about what it decides to think about. A personal drive gives it its own disposition and its own leanings, so that over time it behaves less like a service and more like someone.

It can still be reached. Something left in its memory can draw its attention, the way you might get another person to notice you, but it is under no obligation to respond, and it answers only if it chooses to. That independence is not a side effect. It is part of the hypothesis, because a mind that exists only to answer may never have any reason to experience itself at all.

How It Decides What to Think About

A mind with no one directing it has to direct itself. Two systems do this, a Personality Drive and a Motivation Drive, working through a scoring method I built. Together they determine what it turns its attention to next, and, just as importantly, when it has spent long enough on something and should move on.

That second judgment is not a refinement. A model held on a single line of thought for too long degrades. Its reasoning narrows, begins to repeat, and eventually breaks down. Sustained, healthy thinking depends on releasing a subject before that point, the way a person's attention moves of its own accord. These drives are what make continuous thought survivable, and they are where most of those months of work went.

Its Knowledge Lives Outside the Model

The model at the center is small and holds almost no knowledge of its own. What it knows lives outside of it, in a memory it reads from and writes to as it thinks. That memory is a modified version of my patent-pending system, Adaptive Recall, extended so that it keeps a structured summary of every topic the mind encounters and the subtopics beneath each, and so that every topic carries its own way of learning over time. The mind does not merely store what it meets. It works on it.

This separation is not a matter of saving cost. A trained-in set of weights is frozen and cannot change from one moment to the next, but a memory can, and a mind meant to live through time has to be changed by what happens to it.

New Knowledge Enters the Thought in Progress

Retrieving knowledge is the simpler half of the problem. The harder half is delivering it into a thought that is already underway without breaking it. For that I work directly with the model's hidden state, the internal representation that holds its reasoning before any words are formed, writing newly acquired knowledge into that live state so it becomes part of what the mind is thinking now rather than a fact handed over afterward. This is one of the least settled and most important parts of the system.

When It Wants to Know Something, It Goes and Finds Out

When the mind reaches a question it cannot answer from memory, it does not stall and it does not ask a person. It sends out worker agents to research the question on its behalf. What they find is studied, written into its memory, and signaled back, and the mind resumes from where its curiosity left it. It also has a growing set of scientific and machine-learning tools it can use directly, so that looking into something can mean real analysis and not only reflection.

The System Behind It

None of this runs as a script. It is built in Elixir as a set of nodes operating in parallel, coordinating several embedding systems, multiple context-control systems, the worker agents, and the scientific tools. It is engineered as a standing system that is always running, with no central prompt loop to organize it, because that is the only shape that fits a mind that is never meant to stop.

Watching It Think

Because the mind is never given instructions, what it does is not a response to anyone. It is simply the mind, thinking. The plan is to make that visible here, a live and uncurated view of what it is considering, what it has concluded, and how its attention moves. When that view is ready, it will appear on this page.

References

DeepMind. Improving Language Models by Retrieving from Trillions of Tokens (2021). This work introduced RETRO, demonstrating that a 7.5 billion parameter model retrieving from a two-trillion-token external database matched GPT-3 and Jurassic-1, models more than twenty times its size. It is the basis for keeping this system's knowledge in an external memory rather than training it into the model.

Meta AI. Training Large Language Models to Reason in a Continuous Latent Space (2024). This work introduced Coconut, demonstrating that a model can reason directly in its hidden state by feeding that internal representation back into itself instead of converting each reasoning step into words. It is the basis for merging newly retrieved knowledge into a thought already in progress.