Journal
GCTX: the first full model training and what followed
GCTX completed its first full 93M-parameter training run on September 22. Follow-up experiments show reliable small-set fitting, while useful generalization remains open.
Why I Froze an Imperfect Eval Baseline
A follow-up note on why the July Open Model Lab baseline stays frozen even after the failure audit found grader artifacts, strict-format misses, and token-limit effects.
Open Model Research Harness completes its July evaluation gate
The first Open Model Research Harness gate is complete: 25 tasks, three local open models, 75 scored outputs, a deterministic comparison, and a failure audit that shows why raw pass rates need context.
Starting Open Model Research Harness
A public 12-stage project to build an eval-first research-engineering harness for open LLMs.
Local model memory: bits, dense, MoE
A short note for reading local model memory requirements without confusing active MoE parameters with loaded weights.
GCTX passes its first data-readiness gate
GCTX's data pipeline passed its first volume, split, and format checks for a proof-model run.
Starting GCTX: a small model for Git diffs
A starting note for GCTX, a from-scratch small language model project for reading Git diffs and writing Conventional Commit messages.
chess-zero: the platform's done, the intelligence isn't
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.
A Research-Use Preview of the Gene-Disease Evidence Index
A short note announcing the public preview of the Gene-Disease Evidence Index.
Nexus and the Shape of Information
A note on Yuval Noah Harari's Nexus and how information networks shape trust, power, and AI.
Starting chess-zero
Starting a hand-built chess engine and AlphaZero-style RL pipeline as a learning project for the ML side.