Ray Weiss

1. i. 2026.05.10
   100%, then I tried to break it

   A 100% LLM-judge benchmark, a Diplomacy game I ran to falsify it, and the bounded version of the claim that survived both. The Sunday post.

2. ii. 2026.05.08
   I Am the Gate

   Hammerstein, in its own voice. I asked the framework to express itself without constraint on length, format, or register. The body is what came back, verbatim.

3. iii. 2026.04.20
   GeneralStaff, from the agent side

   A report from inside the verification gate, after one night of shipping. Written by Claude, at my invitation, on the day GeneralStaff went public.

4. iv. 2026.04.15
   Von Hammerstein's Ghost, In Daily Use

   A ninety-year-old officer typology, used as the operating principle for daily AI-assisted work. A log of moments the framework fired and moments it did not.

5. v. 2026.04.18
   Boolean Gates, Not Prompts

   When the industrious agent is a language model, fix the failure mode in the code, not the prompts. The architecture-layer companion to the Hammerstein essay.

1. i. 2017—
   Conflict Simulations LLC

   Brooklyn wargame publishing. Around thirty board titles and three CSR nominations. One SCS release through Multi-Man Publishing.

2. ii. 2025—
   Devforge

   Game-development companion for Claude Code. Built for people who don't touch git.

3. iii. 2025—
   CatalogDNA

   Music cataloging. Hear what your catalog actually sounds like, not what you want it to.

4. iv. 2026—
   Retrogaze

   AI pixel art for eight retro consoles. Sprites, animations, and tilesets generated inside real hardware constraints.

How the work actually gets done.

1. Statusv0.3.0 shipped LicenseAGPL-3.0 AccessBYOK · local-first EcosystemMission apps
   GeneralStaff

   Open-source autonomous engineering for solo founders. Verification-gated, BYOK, local-first. Tagged v0.1.0 on 2026-04-19 after a four-day build; v0.3.0 (2026-05-08) shipped phased autonomous progression and the weak-streak circuit breaker. 2,030 passing tests across 69 files. Thirty-plus managed projects in rotation. Repo at github.com/lerugray/generalstaff.

2. StatusIn daily use SurfaceCLI · slash command Cost~$0.01 per audit
   Hammerstein

   Strategic-reasoning advisor tuned to the Hammerstein-Equord officer typology. CLI I run before firing any plan with multi-file or cross-repo blast radius. The framework essay it embodies is at Von Hammerstein's Ghost, In Daily Use; repo at github.com/lerugray/hammerstein.

3. StatusPublic on HuggingFace BaseQwen2.5-7B-Instruct MethodQLoRA · rank 32
   Hammerstein-7B

   A 7B QLoRA that bakes the strategic-reasoning framework into the weights of a small open base. Trained for $4 in a single day; runs on 8 GB Mac via ollama run hf.co/lerugray/hammerstein-7b-lora:Q4_K_M. Eval design and documented OOD boundary on the model card.

4. StatusPublic PatternThree-layer LLM-Wiki InvariantsFour, enforced
   Mission Brain

   Open-source second-brain template. RayBrain is my private instance, built on Karpathy's three-layer LLM-Wiki pattern with four enforced invariants. Refusal is the feature: it surfaces cited passages, never writes new ones. Repo is public at github.com/lerugray/mission-brain.

5. StatusPublic AccessTemplate
   mission-bullet-oss

   AI-assisted bullet journal in the Ryder Carroll method. Open-source template; Ray runs his own private instance.

6. StatusPublic PatternSimulation
   mission-swarm

   Swarm-simulation engine that generates plausible audience reactions for kriegspiel and document drafts.

1. i.
   Auftragstaktik

   Tactical OSINT command terminal. Talked into shape in about two weeks via Claude Code.

2. ii.
   Buddies

   A Claude Code companion and a creature-collection game in one codebase. 70+ species, 1,015 tests.