Blog

In this blog post, we discuss the application of the free energy principle (FEP) to model real-world data-generating systems, and the question whether the FEP stands on its own as a foundational principle in a purely unsupervised setting. 

We discuss the free energy principle (FEP): What it is, what it is not, what promise it holds, why it can be extremely useful, and why it has yet to live up to the hype.

We comment on a new paper by Silver and Sutton, entitled “Welcome to the era of experience” (2025). Their main argument is that we have entered a new era of research and development in the field of artificial intelligence, which will will be characterized by “grounding” in the real world, online action-perception loops, physical embodiment, environment-sourced reward signals, and online real-time experiential learning. 

Driven by key insights from statistical physics and cognitive science, in particular by Karl Friston’s active inference framework, the approach pioneered at Noumenal Labs unlocks the capability of machines to represent the physical world in the same way we do, enabling them to act safely and in alignment with human values — and thereby, to deliver on the promise of Physical AI.

Inspired by neural reuse and reassembly, we consider key design features that unlock the ability for AI to reason by analogy and by metaphor

We discuss approaches to AI alignment, and in particular, the crucial role of theory of mind, the ability to take the perspective of another

Here we discuss key gaps in SOTA applications of active inference in AI - and how Noumenal Labs is working to fill them.

In this blog post, we describe the new approach to macroscopic physics discovery that we are developing at Noumenal Labs.

The AI systems that we are developing reason about the world like a scientist does.

The two main competitive advantages of the big players in AI no longer ensure market superiority.