Source-first AI systems curriculum
Sylla Reader
Mobile-friendly reading view for the raw course files, labs, rubrics, and platform adapters in this repo.
Course Platform
Open the LearnHouse-hosted course experience for enrollment-style navigation, progress tracking, and platform-native lessons.
Platform-adaptedLocal AI Model Systems
A practical systems course for local LLM inference, MLX internals, model memory budgets, MoE tradeoffs, and DFlash-style speculative decoding.
Source-firstNanoTransformer in MLX
An implementation-first course for building a small decoder-only transformer in MLX and proving it with logits, memory traces, and benchmarks.
Platform-adaptedLocal AI Model Systems Advanced Lab
An advanced systems lab for reading model configs, reasoning about attention and MoE internals, profiling MLX, and evaluating DFlash-style speculative decoding.
Source-firstSpeculative and MoE Systems Lab
An advanced inference systems course for quantization internals, speculative decoding, MoE routing, paged cache allocation, and evidence-driven benchmarks.
Platform-adaptedRecursive Language Models Foundations
A polished builder-track introduction to Recursive Language Models, covering context rot, the official client, and a minimal REPL harness.
Platform-adaptedRecursive Language Models Applied Patterns
An intermediate, workshop-style RLM course on prompt contracts, recursive decomposition, chunking strategy, and workflow design.
Platform-adaptedRecursive Language Models Systems Lab
A rigorous follow-on course on safe execution, evaluation, and architecture tradeoffs for Recursive Language Models.