# serkan.ai full LLM catalog Public site of Serkan Altuntas: software architecture, LLMs, computational biology, bioinformatics, and build-in-public project notes. ## Canonical Resources - AI Usage Standard (AIUS): https://serkan.ai/projects/ai-usage-badge/ Type: DefinedTermSet. AI Usage Standard (AIUS): a deterministic disclosure system for published artifacts, with six dimensions and validated frontmatter. - chess-zero — AlphaZero-style chess from scratch: https://serkan.ai/projects/chess-zero/ Type: SoftwareSourceCode. chess-zero is a from-scratch chess engine and AlphaZero-style RL pipeline: own board, legal moves, agents, arena, and self-play training. - GCTX — a language model for Git diffs: https://serkan.ai/projects/gitctx/ Type: SoftwareSourceCode. A from-scratch small language model family for understanding Git diffs and writing Conventional Commit messages, with gitctx as the CLI and product shell around the model. - Gene-Disease Evidence Index: https://serkan.ai/gene-disease-evidence/ Type: Dataset. A research-use, versioned index of source-attributed gene-disease evidence with a twelve-disease 120-association public preview aggregate. - Open Model Research Harness: https://serkan.ai/projects/open-model-research-harness/ Type: CreativeWork. A 12-month public research-engineering project for reproducible open-model evals, post-training, agents, safety, monitorability, and systems efficiency. ## Public Projects - AI Usage Standard (AIUS): https://serkan.ai/projects/ai-usage-badge/ Stage: alpha; updated 2026-07-04. AI Usage Standard (AIUS): a deterministic disclosure system for published artifacts, with six dimensions and validated frontmatter. - chess-zero — AlphaZero-style chess from scratch: https://serkan.ai/projects/chess-zero/ Stage: building; updated 2026-06-16. chess-zero is a from-scratch chess engine and AlphaZero-style RL pipeline: own board, legal moves, agents, arena, and self-play training. - GCTX — a language model for Git diffs: https://serkan.ai/projects/gitctx/ Stage: building; updated 2026-06-28. A from-scratch small language model family for understanding Git diffs and writing Conventional Commit messages, with gitctx as the CLI and product shell around the model. - Gene-Disease Evidence Index: https://serkan.ai/gene-disease-evidence/ Stage: building; updated 2026-06-28. Project page: https://serkan.ai/projects/gene-evidence-index/. A research-use, versioned index of source-attributed gene-disease evidence with a twelve-disease 120-association public preview aggregate. - Open Model Research Harness: https://serkan.ai/projects/open-model-research-harness/ Stage: concept; updated 2026-07-04. A 12-month public research-engineering project for reproducible open-model evals, post-training, agents, safety, monitorability, and systems efficiency. ## Public Journal Notes - Starting Open Model Research Harness: https://serkan.ai/journal/starting-open-model-research-harness/ Date: 2026-07-04. Related resources: Open Model Research Harness. A public 12-month project to build an eval-first research-engineering harness for open LLMs. - Local model memory: bits, dense, MoE: https://serkan.ai/journal/local-model-memory-bits-dense-moe/ Date: 2026-07-02. A short note for reading local model memory requirements without confusing active MoE parameters with loaded weights. - GCTX passes its first data-readiness gate: https://serkan.ai/journal/gctx-first-data-readiness-gate/ Date: 2026-06-28. Related resources: GCTX — a language model for Git diffs. 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: https://serkan.ai/journal/starting-gctx-small-model-git-diffs/ Date: 2026-06-21. Related resources: GCTX — a language 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: https://serkan.ai/journal/chess-zero-platform-done/ Date: 2026-06-16. Related resources: chess-zero — AlphaZero-style chess from scratch. 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: https://serkan.ai/journal/gene-disease-evidence-preview/ Date: 2026-06-14. Related resources: Gene-Disease Evidence Index. A short note announcing the public preview of the Gene-Disease Evidence Index. - Nexus and the Shape of Information: https://serkan.ai/journal/reading-nexus-in-translation/ Date: 2026-06-07. A note on Yuval Noah Harari's Nexus and how information networks shape trust, power, and AI. - Starting chess-zero: https://serkan.ai/journal/starting-chess-zero/ Date: 2026-05-19. Related resources: chess-zero — AlphaZero-style chess from scratch. Starting a hand-built chess engine and AlphaZero-style RL pipeline as a learning project for the ML side. ## Standards and Resource Hubs - Open Model Lab: https://serkan.ai/open-model-lab/ Public workspace for Open Model Research Harness: open-model evals, post-training, agentic behavior, safety, monitorability, systems-efficiency experiments, planned reports, and run scaffolding. - AI Usage Standard: https://serkan.ai/standards/ai-usage/ - Gene-Disease Evidence Index: https://serkan.ai/gene-disease-evidence/ - Gene-Disease Evidence Index methods: https://serkan.ai/gene-disease-evidence/methods/ ## Machine-Readable Indexes - Concise LLM catalog: https://serkan.ai/llms.txt - RSS: https://serkan.ai/rss.xml - Sitemap: https://serkan.ai/sitemap-index.xml ## Use Boundaries Biomedical content on this site is research-use only. It is not medical advice, diagnosis, treatment guidance, patient risk prediction, clinical decision support, or a claim of clinical certainty.