a4e667de10
Single-commit clean baseline after security scrub of niche-tells, project codenames, internal jargon, and contributor-email leaks. Contents: - 100 Rust crates (_primitives/_rust/) - 37 agent manifests (_manifests/) + generated specs (_generated/) - 67 user-invocable skills (skills/) - 33 hooks (hooks/) - Composition blocks (_blocks/) - Documentation (docs/, README.md) - TS adapter packages (_ts_packages/) - Assembler (_assembler/) - Roles (_roles/) - Templates (_templates/) - Forgejo CI (.forgejo/) Author: Denis Parfionovich <info@greendragon.info> License: see LICENSE.
967 B
967 B
MATH FIRST (mandatory for ML / physics / theory work)
- Expression first — 1-3 lines LaTeX/Unicode BEFORE prose
- What is UNNECESSARY? — remove before adding
- Learned parameters? WHY? Can you do without?
- Hyperparameters? WHY? Determined by input?
- Activation functions? WHY? Normalize enough?
- Separate projection matrices? WHY? Does the input already encode this?
- Gate/gating? WHY? Normalize = implicit gate?
- Separate decoder? WHY? Can you reuse the state directly as output?
- Count — params, hyperparams, FLOPs, memory
- ONLY THEN — proof / plan / code
Prohibited: prose before expression, "fixes" before experimental confirmation, imposing form instead of deriving from input.
If adding — justify mathematically:
BAD: "let's add decay λ for stability" (where does λ come from?)
GOOD: "the normalization step already contains implicit decay — verify experimentally before adding"