01
AI agents · Lean
The Organism - My Lean based spin on the Wheelhouse
An autonomous research lab with Lean at its core, and a look at what happens when the agents build their own working environment.
02 / The notebook
A trail of thoughts.
Research notes, useful wrong turns, and things I needed to write down to understand. Originally published on Substack; collected here for a quieter read.
9 entries in the notebook
11 min read
02
Formal verification · Lean
Certified Research Reduction Graphs
Keeping the original mathematical question intact as autonomous agents split, refine, and revisit research obligations.
03
Prover optimization / Chapter 5
The future of Snark Autoresearch
From performance optimization to cryptographic research: what a more complete autoresearch loop would need.
04
AI · Policy
Why Frontier AI Regulation proposals will result in Regulatory Capture by Design
A critique of frontier AI regulation through the lens of incentives, competition, and regulatory capture.
05
AI · Thinking
The Inversion
A personal thesis on generalists, domain expertise, and what changes when AI makes more of the building accessible.
06
Prover optimization / Chapter 4
How we got to 40% faster proving on Lean Ethereum zkVM?
The leanVM chapter: moving from isolated micro-optimizations to profiling, algorithmic changes, and end-to-end measurement.
07
Prover optimization / Chapter 3
How well can you use the autoresearch methodology to develop a new product or feature?
The allocator detour: using the autoresearch loop to build a new tool, then testing where it helps and where it does not.
08
Prover optimization / Chapter 2
Plonky3 Monty-31 Optimization — Model Scaling Experiment - zk-autoresearch
A Plonky3 experiment comparing model scaling with the ability to retain context, question a benchmark, and change direction.
09
Prover optimization / Chapter 1
zk-autoresearch Experiment 1
The first Plonky3 experiment: applying an autonomous optimization loop to an already optimized production proving framework.