I am currently focused on agent infrastructure and orchestration: systems that let models act with high leverage without collapsing observability, safety, or operator control. The through-line from robotics to defense ML to production AI has converged into one design mandate: calibrated intelligence under real constraints.
Conviction
The Bitter Lesson still governs: scalable computation compounds; bespoke scaffolding accretes debt. Much of today’s agent tooling inverts that truth by relocating intelligence from learnable substrates into brittle orchestration code.
I want harnesses to remain thin, explicit, and replaceable. Let the model absorb complexity; keep the interface accountable. A practical criterion: if model capability doubles next year, your system should simplify rather than metastasize.
Interests
- Agent DX
- Interfaces designed for how agents actually work, not how we wish they worked. Recursive delegation, context isolation, deterministic control flow.
- Interpretability arbitrages
- Sparse autoencoders as first-class citizens. The less you understand it, the more GPUs it takes.
- Specialized language models
- Late interaction, sparse encoding, modular manifolds, matroshka embeddings.
- Configurancy
- Keeping systems intelligible while agents write all the code.
- Context engineering
- Prompt optimization and context distillation as underexplored primitives for post-training pipelines.
Philosophy
Simplicity over speed. Correctness over features. Sensemaking, justifying intuition, scaling intention—I’ve been using AI tools for this since GPT-3, intentionally iterating on effective collaboration. Not just using the tools, but interrogating how to use them well.
The value of a 10K-line Python library is approaching $1 in 2026. What survives are systems that compress hard-won insights agents would have to rediscover at enormous token cost. Systems that operate on a cheaper substrate than inference. Systems that solve hard universal problems agents can’t route around easily.
Excited about designing simple affordances within complex environments.