Journal

Starting Open Model Research Harness

Jul 4, 2026 · note

A public 12-month project to build an eval-first research-engineering harness for open LLMs.

co-authored i0·r1·d1·e2·c1·v0 — Co-Authored

Local model memory: bits, dense, MoE

Jul 2, 2026 · note

A short note for reading local model memory requirements without confusing active MoE parameters with loaded weights.

ai-led i0·r0·d3·e3·c0·v3 — AI-Led

GCTX passes its first data-readiness gate

Jun 28, 2026 · note

GCTX now has enough reviewed DEV and locked REPORT data to start the first 60M-100M proof language-model run.

ai-led i0·r1·d3·e3·c0·v0 — AI-Led

Starting GCTX: a small model for Git diffs

Jun 21, 2026 · note

A starting note for GCTX, a from-scratch small language model project for reading Git diffs and writing Conventional Commit messages.

ai-led i0·r1·d3·e3·c0·v0 — AI-Led

chess-zero: the platform's done, the intelligence isn't

Jun 16, 2026 · note

A month in, chess-zero has a complete, verified chess platform and no learned intelligence yet — the hand-written ML pipeline is what comes next.

co-authored i0·r0·d1·e2·c0·v0 — Co-Authored

A Research-Use Preview of the Gene-Disease Evidence Index

Jun 14, 2026 · note

A short note announcing the public preview of the Gene-Disease Evidence Index.

ai-led i0·r0·d3·e3·c0·v0 — AI-Led

Nexus and the Shape of Information

Jun 7, 2026 · note

A note on Yuval Noah Harari's Nexus and how information networks shape trust, power, and AI.

co-authored i0·r0·d0·e2·c0·v0 — Co-Authored

Starting chess-zero

May 19, 2026 · note

Starting a hand-built chess engine and AlphaZero-style RL pipeline as a learning project for the ML side.

ai-assisted i0·r0·d0·e1·c0·v0 — AI-Assisted