Learn LLM internals step by step - from tokenization to attention to inference optimization.

We read all 512K lines of Claude Code's accidentally exposed source. 82 docs, 15 diagrams, every subsystem mapped — from the hidden YOLO safety classifier to multi-agent swarms.

A reference point for phenomena that have been reported to occur inside AI systems but have no direct mapping into natural language.

Mechanistic interpretability of transformer hallucinations via attention flow, residual stream geometry, and head-level attribution analysis.

"A theoretical framework and implementation for governing LLMs via Digital Wave Dynamics, latent space topology, and non-linear state control." "A mathematical and physical approach to LLM internals: Exploring digital wave mechanics, topological manifolds, and mechanistic interpretability."

Testing whether RLHF instills a privileged self-emotion direction in the residual stream, and whether surgical steering on emotion sub-directions can decouple sycophancy from harshness. Open-weight replication on Qwen2.5-32B.

Analyze Claude Code source leaks with static reviews, architecture notes, security findings, memory flow, and tool integration details

Analyze Claude Code’s architecture, modules, and design patterns to understand its internals and build better tools and integrations