Module 1
How artificial intelligence transforms words into coordinates in a space we cannot see. But can learn to understand.
Every word in every language maps to a token ID. The same concept, different surfaces. All pointing to numbers in a shared vocabulary of roughly 100,000 tokens.
Six languages. Six different words. Six different token IDs. But when these tokens become vectors, they all point to the same neighborhood in meaning-space. The AI does not translate. It navigates to where the concept lives.
Each token ID becomes a vector: a list of 12,288 numbers. Each number is a coordinate in a dimension we cannot visualize, but the model navigates fluently.
In the film Interstellar, the tesseract allowed Cooper to perceive time as a spatial dimension, seeing his daughter's bedroom across all moments simultaneously. We face a similar challenge. How do you show a space with 12,288 dimensions to beings who can only perceive three? The answer: we show shadows, projections, and relationships. We cannot see the space, but we can see what it does.
In this high-dimensional space, concepts cluster together. Words from different languages that mean the same thing are neighbors. Related ideas form gravitational wells of meaning.
This is a 2D projection of a 12,288-dimensional reality. "Insurance" in English and "seguro" in Spanish are neighbors in this space. Not because anyone told the AI they mean the same thing, but because they appear in similar contexts across billions of sentences. The model learned the map of meaning by walking through language.
Like Cooper in Interstellar perceiving time as space, the AI perceives meaning as geometry. Each word exists at coordinates we cannot see, but the machine navigates fluently.
This is a conceptual model, not a technical specification. The metaphors are simplified to build intuition for how to work with AI effectively. If you want the engineering details—transformers, attention mechanisms, next-token prediction—ask Claude or Perplexity to go deeper.