How mmonad/feynman works
This repository is primarily a Feynman-style LLM and machine-learning tutoring curriculum, organized as topical course directories containing lesson documents. A learner chooses a course and follows its lessons; the README describes a progression from adaptation methods to verification, cryptography, and broader ML theory. The tree also contains two distinct research tools: token-level entropy evaluation and hidden-state topology experiments. Their internal edges below are limited to relationships visible in the supplied source index or excerpts; the curriculum’s lesson-level content and unsampled implementations are not expanded.
Main entry points: run.py Entropy Evaluation · run_experiment.py TDA Experiment · course-1-icl-vs-finetuning ICL vs Fine-Tuning · course-2-lora LoRA
Components 31
LLM Adaptation
- ICL vs Fine-Tuning
course-1-icl-vs-finetuning - LoRA
course-2-lora - Self-Improving Harness
course-5-self-improving-harness - LoRA Practice
course-19-lora-practice
Verification Systems
- Adapter Committees
course-3-orthogonal-adapters-code-review - Verification Enterprise
course-4-from-architecture-to-enterprise
Cryptography
- Crypto Foundations
course-6-crypto-foundations - Crypto Toolkit
course-7-crypto-toolkit - BABE Protocol
course-8-babe-protocol
ML Foundations
- Remedial Topics
course-9-remedial - Statistical Learning
course-10-statistical-learning-theory - Optimization
course-11-optimization - Probabilistic ML
course-12-probabilistic-ml - Deep Learning Theory
course-13-deep-learning-theory - Vision and NLP
course-14-vision-and-nlp - Reinforcement Learning
course-15-reinforcement-learning - Generalization and GNNs
course-16-generalization-and-gnns - Causality and Practice
course-17-causality-and-practical-ml - Robustness Frontier
course-18-systems-robustness-frontier - Intelligence Theory
course-20-mathematical-theory-of-intelligence
Research Tools
- Entropy Evaluation
llm-information-theory/run.py - FineWeb Holdout
llm-information-theory/data.py - Model Loader
llm-information-theory/models.py - Windowed Scoring
llm-information-theory/windowed_eval.py - Entropy Report
llm-information-theory/report.py - TDA Experiment
llm-topology-tda/run_experiment.py - Benchmarks and Graders
llm-topology-tda/datasets_lib.py - State Extraction
llm-topology-tda/pipeline.py - PCA and Persistence
llm-topology-tda/analyze.py - Failure Landscape
llm-topology-tda/failure_landscape_tda.py
Other components
- Learner
Connections 26
- Learner → ICL vs Fine-Tuning: studies lessons
README.md - Learner → LoRA: studies lessons
README.md - Learner → Adapter Committees: studies lessons
README.md - Learner → Verification Enterprise: studies lessons
README.md - Learner → Self-Improving Harness: studies lessons
README.md - Learner → Crypto Foundations: studies lessons
README.md - Learner → Crypto Toolkit: studies lessons
README.md - Learner → BABE Protocol: studies lessons
README.md - Learner → Remedial Topics: studies lessons
README.md - Learner → Statistical Learning: studies lessons
README.md - Learner → Optimization: studies lessons
README.md - Learner → Probabilistic ML: studies lessons
README.md - Learner → Deep Learning Theory: studies lessons
README.md - Learner → Vision and NLP: studies lessons
README.md - Learner → Reinforcement Learning: studies lessons
README.md - Learner → Generalization and GNNs: studies lessons
README.md - Learner → Causality and Practice: studies lessons
README.md - Learner → Robustness Frontier: studies lessons
README.md - Learner → LoRA Practice: studies lessons
README.md - Learner → Intelligence Theory: studies lessons
README.md - Entropy Evaluation → FineWeb Holdout: loads holdout
llm-information-theory/run.py - Entropy Evaluation → Model Loader: loads model
llm-information-theory/run.py - Entropy Evaluation → Windowed Scoring: scores documents
llm-information-theory/run.py - TDA Experiment → Benchmarks and Graders: loads and grades
llm-topology-tda/run_experiment.py - TDA Experiment → State Extraction: extracts states
llm-topology-tda/run_experiment.py - TDA Experiment → PCA and Persistence: runs analysis
llm-topology-tda/run_experiment.py