AI Engineering from Scratch tops 65k GitHub stars: 523 lessons from raw math to agent loops
bigaiguy · x · 2026-10-15
rohitg00's open-source curriculum AI Engineering from Scratch just crossed 65k GitHub stars:
- 20 phases, 523 lessons (342 hours), Python/TypeScript/Rust/Julia, free and MIT-licensed.
- Counterintuitive approach: every algorithm — backprop, tokenizer, attention, the agent loop — is built from raw math before any framework appears, so PyTorch holds no mystery.
- Each lesson ships a reusable artifact instead of a certificate: a prompt, a skill, an agent, or an MCP server you drop into your own workflow — 523 tools you build yourself.
- 114k readers and 182k page views in 30 days; the README cites that 84% of students already use AI tools but only 18% feel professionally prepared.
More from coding & agent
- Python 3.15 ships: lazy imports, frozendict, and a faster experimental JIT — _jaydeepkarale · 2026-10-15
- "Agentic coding 10x's developers" — the code, the bugs, and the people pretending to read the diff — blaizedsouza · 2026-10-15
- OWASP publishes Non-Human Identities Top 10 for securing machine and AI agent identities — gleech · 2026-10-15
- Hot Take: Agentic Automation of Mundane IT Is a Gold Mine — and Extremely Hard — Paimaamu · 2026-10-15
- Open-source 386-page 3D Vibe Coding handbook: GPT-Image to Tripo to Blender, with playable demos — AlchainHust · 2026-10-15
- Simple Trick for Better AI Agent Runs: Tell It What NOT to Touch — thisiskp_ · 2026-10-15