The Viable System Model & Multi-Scale Agency
Stafford Beer & The Quest for understanding general agents
Equilibria Network
Equilibria Network is a non-profit research organisation looking into the foundations of collective intelligence as it relates to AI. We bring methods from complex systems sciences to try to find partial solutions to problems like Gradual Disempowerment.
Live Last read · last published · next check
Latest posts
Models of Society Are Built on Models of Agents
Part 1 of a series on process alignment, a different way of thinking about agents at every scale.
A Taxonomy of Agents: Intro & Request for feedback
AI was used to translate around 20 minutes of talking out the entire post.
A Compositional Philosophy of Science for Agent Foundations
I describe the philosophy of science that I follow when it comes to the research that I do.
Systemic Risks and Where to Find Them
Or: Todd Has a Presentation in London on Thursday and Three Academics (Some of Them Dead), Won’t Stop Arguing About Root Fungi
Spectral Signatures of Gradual Disempowerment
TL;DR AI disempowerment operates across markets, networks, and governance simultaneously, but our analytical tools don’t cross those boundaries.
The Atoms of Knowledge Aren't Universal
Why DeSci should stop searching for universal verification and start building compositional translations.
System Level Safety Evaluations
Adversarial evaluations test whether safety measures hold when AI systems actively try to subvert them. Red teams construct attacks, blue teams build defenses, and we measure whether containment protocols survive adversarial pressure. We are building evaluations to test whether entire societal defensive processes can maintain their core functions when facing coordinated attacks from multiple…
A Phylogeny of Agents
In Douglas Hofstadter's "Gödel, Escher, Bach," he explores how simple elements give rise to complex wholes that seem to possess entirely new properties.