Noumenal Labs White Paper: How To Build A Brain

2025-02-16

AI Summary

This paper addresses the foundational challenge in AI—designing machine intelligence that augments, rather than replaces, human understanding and agency. The core difficulty lies in constructing world models grounded in physical reality to support human-like world representations and scientific-style knowledge generation from prior knowledge. Method: We propose the “Rational Empirical Modeling Paradigm,” inspired by the scientific method, which jointly enforces causal physical discovery capability and human-level representational groundedness. Our approach integrates 3D embodied world modeling, multimodal temporal reasoning, causal inference, and embodied cognitive architectures. Contribution: We establish design principles for AI systems explicitly oriented toward enhancing human understanding, and provide a scalable pathway to causal intelligence—moving beyond the current language-model-dominated paradigm. Our framework bridges symbolic and subsymbolic reasoning, enables interpretable causal abstraction, and supports iterative hypothesis testing in physically grounded environments.

Technology Category

• Intelligent Robots: Embodied AI
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

This white paper describes some of the design principles for artificial or machine intelligence that guide efforts at Noumenal Labs. These principles are drawn from both nature and from the means by which we come to represent and understand it. The end goal of research and development in this field should be to design machine intelligences that augment our understanding of the world and enhance our ability to act in it, without replacing us. In the first two sections, we examine the core motivation for our approach: resolving the grounding problem. We argue that the solution to the grounding problem rests in the design of models grounded in the world that we inhabit, not mere word models. A machine super intelligence that is capable of significantly enhancing our understanding of the human world must represent the world as we do and be capable of generating new knowledge, building on what we already know. In other words, it must be properly grounded and explicitly designed for rational, empirical inquiry, modeled after the scientific method. A primary implication of this design principle is that agents must be capable of engaging autonomously in causal physics discovery. We discuss the pragmatic implications of this approach, and in particular, the use cases in realistic 3D world modeling and multimodal, multidimensional time series analysis.

Problem

• Design principles for artificial intelligence
• Resolving the grounding problem
• Autonomous causal physics discovery

Innovation

• grounded in the world
• causal physics discovery
• 3D world modeling