The dojo and the sensei

The dojo grades every answer with the engine, never with the model: you build an automaton, grammar or Turing machine, and the grader compares it against a reference over a shared work budget. Solutions are revealed only when you give up. The pumping drill and the NP lab run entirely offline.

Where problems come from

The model only proposes. Every generated problem carries a reference solution plus example words, and the engine must agree with all of them before the problem is shown; a 4-attempt repair loop feeds engine errors back to the model. For Turing machines the model only phrases the task; the reference comes from a hand-verified library of nine machines, because models rarely write correct TMs.

Choosing a model

Problems were measured with the app’s own validation loop against the live engine: 10 generated problems per model, each counted only if the reference agreed with every example (the same bar the dojo enforces before showing a problem):

Model Sound within 4 attempts Avg. time
google/gemini-3.1-flash-lite (default) 9 / 10 ~2 s
deepseek/deepseek-v4-flash 4 / 5 ~15 s
deepseek/deepseek-v3.2 4 / 5 ~19 s
google/gemini-2.5-flash-lite 2 / 5 ~5 s
anthropic/claude-haiku-5.5 1 / 5 ~17 s

Connecting a brain

OpenRouter

DOJO → SENSEI'S BRAIN → paste an API key from openrouter.ai. The model field defaults to the verified minimum above.

Ollama

Point the base URL at http://localhost:11434/v1; start Ollama with OLLAMA_ORIGINS=<this app's origin> so the browser may call it. Local models are weaker: the engine still re-validates everything, so a bad model shows up as failed generations, never as wrong grades.

Custom

Any OpenAI-compatible /chat/completions endpoint: paste the base URL and, if the endpoint needs one, an API key.