Now · A decision simulator
SupaSim lets organisations simulate their decisions before implementing them in the real world.
Neurosymbolic AI research
Machines that dream.
It's downright absurd.
We're experimenting at the intersection of generative AI and symbolic world models. The intention is to build AI systems that learn from their interactions.
Why
From prediction to thinking.
Today's AI systems can write, code, perceive, retrieve, and act. But in complex environments, they often fail to build persistent models of cause and effect.
They can describe relationships without reliably representing them. They can use context without accumulating understanding. They can act without knowing how their theory of the world should change when predictions fail.
We believe the next generation of AI will need more than larger models and longer context windows. It will need systems that construct, test, refine, and use explicit models of the world.
What
Neural intuition. Symbolic structure.
Dwnrt Absrd is a neurosymbolic AI research lab.
Foundation models provide perception, language, intuition, and flexible generalization. Symbolic world models provide structure, memory, simulation, interpretability, and explicit reasoning.
We're exploring how they can work together to form systems that learn continuously from interaction and evidence.
PerceiveRecognise objects, states, patterns, and changes.
ModelRepresent mechanisms, feedback loops, actions, and consequences.
SimulateExplore possible futures before acting.
PredictMake expectations explicit and testable.
ReviseUpdate internal models when evidence contradicts them.
RememberCarry forward structured understanding across sessions.
Goal
World models that evolve.
Our long-term research goal is the development of causal agents: AI agents that learn, reason, and remember through evolving models of the world.
A causal agent observes an environment, forms hypotheses, predicts outcomes, notices failed predictions, repairs its theory, and uses that evolving understanding to plan better.
Learning is not the accumulation of text. It is the refinement of a world model.
Belief
Action generates information.
We're building.
Some of what we build will be useful. Some of it may just be for fun. The point is to keep learning from contact with reality.
Apps, prototypes, simulations, and playful experiments give us something real to observe: what people try, where systems fail, what surprises us, and what a model needs to learn next.
Application
SupaSim
Our flagship application of our work on integrating causal models with LLMs.
Next · A company brain
The vision is for SupaSim to serve as a company brain by creating an evolving executable mental model of the organization.
SupaSim starts by helping teams test decisions. Over time, its modelling capabilities can build a deeper, persistent understanding of how an organization works.
ARC-AGI
The proving ground
We use ARC-AGI as a proving ground for agents that learn explicit models of unfamiliar worlds through interaction.
Our approach combines vision-language models, foundation models, symbolic world models, and simulation. Agents perceive unfamiliar environments, construct explicit models, test hypotheses through simulation and interaction, and refine their internal world model when predictions fail.
Contact
Build with us.
If you are interested in neurosymbolic AI, causal agents, simulation, systems thinking, or AI that learns how the world works, we'd love to hear from you.
