Motif of the Mind

Work

What I'm working on

Less a portfolio than a map of what I'm pulling on right now — and the questions underneath it. Most of it is built in the open; if a thread interests you, come build.

Thinking with AI agents — knowledge as process

Could LLMs generate real knowledge? Yes — but there's an even lower-hanging fruit: explaining and correcting one surfaces your own tacit knowledge — working with an agent is a form of teaching, and teaching is how you find out what you actually know. I'm building and writing to test that in public.

  • Creator

    agent-team

    A disciplined multi-agent workflow for developing the BlackJAX ecosystem — roles plus a worklog of threads, decisions, and lessons as a knowledge substrate.

    • agents
    • open-source

  • Open-source contributor

    sagent

    Multi-provider agent CLI and Python library.

    • agents
    • open-source

  • Creator

    tuningfork

    A sampler benchmark built on the garden of forking paths: the branches that fail aren't waste, they're knowledge. Failure path as knowledge.

    • Bayesian
    • benchmark
    • open-source

Essays on this, as they land — see Writing.

Probabilistic programming & Bayesian computation

Making rigorous Bayesian inference composable, fast, and genuinely usable — maintained in the open, with a community I care about.

  • Sole developer & curator

    BlackJAX

    Composable, fast Bayesian inference in JAX — samplers as building blocks, with the sampling-book companion of tutorials and worked recipes.

    • Bayesian
    • JAX
    • open-source

  • Core developer

    PyMC

    A leading probabilistic programming library in Python for Bayesian modeling and inference.

    • Bayesian
    • PPL
    • open-source

  • Contributor

    TensorFlow Probability

    Probabilistic reasoning and statistical analysis — contributions to tfp.mcmc.

    • Bayesian
    • MCMC
    • open-source

  • Co-author

    Bayesian Modeling and Computation in Python

    A hands-on book on Bayesian modeling and computation (Martin, Kumar, Lao; CRC Press, 2021).

    • book
    • Bayesian

Roots — cognitive science

Before Bayesian computation I trained as a cognitive scientist — a PhD and postdoc studying how culture shapes visual perception. Underneath the experiments were larger, less testable questions I never stopped turning over: how a mind models other minds, and how cognition and consciousness might arise from computation. They were closer to philosophy than experiment then, and still are. The LLM/agentic era has pulled them back into the light, so I'm slowly writing them down — clearly marked as speculation.

From that era: iMap4, a toolbox for statistical fixation mapping of eye-movement data.

Speculative · not peer-reviewed · revisiting, not predicting.