Serkan Altuntaş

Software Architect in Istanbul, with a computational biology background. Learning LLM systems in public through open-model evals, small-model training, and reproducible engineering notes.

Latest in Journal

Open Model Research Harness completes its July evaluation gate

Jul 29, 2026 · note · 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

Jul 4, 2026 · note · A public 12-month project to build an eval-first research-engineering harness for open LLMs.

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.

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.

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.

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.

All journal notes →

Featured Projects
Open Model Research Harness Building

A 12-month public research-engineering project for reproducible open-model evals, post-training, agents, safety, monitorability, and systems efficiency.

Fresh 8% Next: August 2026: SFT Pipeline + Data Quality
AI Usage Standard (AIUS) Alpha

AI Usage Standard (AIUS): a deterministic disclosure system for published artifacts, with six dimensions and validated frontmatter.

Fresh 54% Next: Phase 2 — npm package (@serkanaltuntas/ai-usage-badge)
Gene-Disease Evidence Index Building

A research-use, versioned index of source-attributed gene-disease evidence with a twelve-disease 120-association public preview aggregate.

Active 91% Next: Complete final public access evidence, existing-resource comparison, source freshness/freeze checks, and DOI/no-DOI archive decision

All projects →

About

Fifteen years of software, with a computational biology and bioinformatics background. Currently working through LLM systems in public: open-model evals, small-model data pipelines, post-training experiments, and reproducible reports with explicit claim boundaries.

Full bio →