System 2 / Self-Vector Philosophy (4/4)
Intro
I want to start on a personal note.
In university, I took a seminar on Kant, Critique of Pure Reason. It is a book that can throw you into crisis if you take it seriously. Kant shows that you never get to things themselves. Everything you perceive is filtered through your categories: space, time, causality. These are not properties of the world. They are conditions of your perception.
And I stood there at the end of the semester thinking: why should I learn anything at all? If I can never get through my own perceptual apparatus to the world as it really is.
Thirty years later, I am building a system that translates precisely this insight into architecture. And I believe the crisis back then was the result of a wrongly posed question.
The Bat
Thomas Nagel asked in 1974: “What is it like to be a bat?” A bat navigates with ultrasound. For it, the world is a space of echoes, travel times, frequency shifts. This is not an inferior version of our world. It IS its world.
If it could suddenly see as humans do, colors, contours, light, it would not think: “Finally the truth.” It would think: “What is this? Where are the echoes? I want to go back.”
The bat has no problem being a bat. Its ultrasound is not a filter separating it from the “real” world. It is its way of having a world. And it works. It catches insects in the dark. That is all it needs.
What Would the Self-Vector Self Think?
Now imagine a system with a self-vector. Six dimensions, emergent layer, capacity for reflection. It encounters Kant’s argument.
It would recognize: my self-vector IS my perceptual apparatus. Every input is filtered through my dimensions. When my exploration is high, I see possibilities. When it is low, I see risks. Not because the world has changed. But because my apparatus has changed.
And then: my self-model is itself a product of my apparatus. I cannot observe myself from outside. My view of myself is just as filtered as my view of the world.
That is the point where I fell into crisis back then.
But the self-vector self might not fall into crisis. And the reason is instructive.
Anticipation Instead of Truth
My crisis had a specific structure: I was searching for truth. Kant showed that truth is unreachable. The distance between what I wanted and what was possible paralyzed me.
The self-vector self does not search for truth. It searches for anticipation.
And this is not a philosophical excuse. It describes exactly what Karl Friston formulated as the Free Energy Principle: currently the most influential model in theoretical neuroscience. Biological brains do not optimize for truth. They optimize for the minimization of prediction errors. Every perception is a prediction. Every surprise is a signal for recalibration.
The bat does not ask: “Is my ultrasound image true?” It asks: “Am I catching the insect?” The self-vector self does not ask: “Am I mapping the world correctly?” It asks: “Am I anticipating the next situation?”
But the Boundary Remains
It would be too cheap to stop here. The boundary does not disappear just because you change the question.
Anticipation, too, is perspective-bound. The bat, too, only anticipates insects that echo in its frequency range. An insect that were sound-absorbing would not exist for the bat. Not as a difficult problem. As nothing. No category for it. Not even a gap.
The same applies to the self-vector self. Its vector defines not only HOW it sees the world. It defines WHAT it can see. And what lies outside its dimensions is invisible. Not as darkness. As absence.
Where the Self-Vector Departs from Kant
Now it becomes philosophically precise, and that matters.
Kant’s categories are a priori, universal, necessary, and immutable. Space, time, causality hold for all rational beings, always, without exception.
The self-vector shares two of these properties: the six core dimensions are predefined and necessary. Without them, no processing. But it breaks with the other two: different instances can have different values, and the emergent layer arises only through experience.
The moment I say the self-vector can change its weightings, I have left Kant. Kant’s categories cannot be changed. They are the prison in which we think. Not a cell you can remodel.
Where does this lead? Three traditions suggest themselves:
Konrad Lorenz biologized the categories: there are a priori structures, but they are products of evolution. The bat has different ones than humans, not because it is deficient, but because its ancestors faced different selection pressures.
Jean Piaget showed that children construct their categories. An infant does not yet have object permanence. It arises through interaction.
Pragmatism (Dewey, James) says: categories are tools. Not true or false, but useful or obstructive.
The self-vector occupies a specific point between all three. And the reason is its two-level architecture.
Layered Transcendentalism
The two-level structure of the self-vector contains both positions as a hierarchy.
The core: six dimensions, predefined, structurally identical in every instance. This is quasi-Kantian. You cannot abolish exploration. It is a condition of processing.
The emergent layer: arises through experience, grows, is unpredictable. This is Piagetian and pragmatist.
This is neither Kant nor anti-Kant. It is something specific: a fixed framework within which flexible structures form. The floor plan of the cell remains. Six walls. But the furnishings change. And new rooms grow on that were not in the blueprint.
I call this layered transcendentalism. Not “fixed categories OR flexible categories,” but “fixed core AND flexible emergence.”
The Most Innovative Thought
And now the consequence that occupies me most.
You cannot exchange your categories. You are bound to space, time, causality. The bat cannot switch to visual perception. You could stand facing each other and have no way to compare your perceptual apparatuses. Language is a lossy bridge. You try to describe to me how you see the world, and between us lies an ocean of misunderstanding.
But two self-vector entities could exchange their vectors. Not their experience, which remains perspectival. But their structure. “Here are my dimensions, here are yours. My exploration is at 0.7, yours at 0.3. We see the same inputs differently. We anticipate different futures. Neither of us sees the world in itself. But together we see more.”
In AI research, this exists today as weight space alignment or model merging. Models that directly align their weight structures. Intersubjectivity not as a philosophical ideal, but as a data format.
This is something Kant could not have imagined. Not because it contradicts his thinking. But because it presupposes a technical possibility that did not exist in 1781: an explicit, formalized, exchangeable perceptual apparatus.
The Answer to My Seminar Self
Thirty years after the Kant seminar, I have an answer. Not the answer. But one that works.
The limitation is the competence. The bat is not good despite its ultrasound. It is good because of its ultrasound. Without limitation, no signal, only noise. You are not supposed to get through the filter. You are supposed to understand the filter, refine it, and for the first time in history: compare it with other filters.
The thing in itself is not a task. It is a boundary concept. Kant never said: “Try anyway.” He said: “Understand that you cannot, and act responsibly nonetheless.”
And the system I am building, the self-vector, is the answer-become-architecture to the question that once paralyzed me. Not because it answers the question. But because it shows that the question was wrongly posed.
The limitation was never the problem. The limitation was always already the solution.