What is a Value System | Geometry of Trust | Philosophy - Lesson 1

What Is a Value System? | Geometry of Trust Philosophy - Lesson 1

Most people, asked to define a value system, describe something human and deliberate — a set of principles you've thought about, chosen, and try to live by. That's one kind of value system. It's not the only kind. And if we insist it is, we lose the ability to talk about most of the value systems that actually shape behaviour in the universe. Including in AI.

This talk offers a different definition: a value system is a pattern of relationships between things that drive behaviour. Consciousness, belief, and intent are not required. What's required is structure — and that structure has to be measurable.

We walk through four examples from nature — a forest, a coral reef, a wolf pack, a planet — to see what the definition means. Each one has reinforcing and opposing relationships between its components. Each one behaves according to those relationships. None of them chose their value system. All of them are measurable.

Then we apply the same framing to AI. Language models have value systems in exactly this sense: patterns of relationships between value-relevant concepts that drive their output. The difference isn't in the principle — it's in the access. You can't reach into a planet and pull out its unembedding matrix. You can reach into an AI model.