Open-source 'AI Engineering from Scratch' course makes you build every algorithm from raw math
ghumare64 · x · 2026-10-24
- AI Engineering from Scratch is a free, MIT-licensed open curriculum by Rohit Ghumare built on a "raw math first" principle: backprop, tokenizers, attention, and the agent loop are all derived and implemented by hand before any framework is introduced.
- Lessons span linear algebra to autonomous swarms, each in four languages (Python, TypeScript, Rust, Julia), following a fixed loop: read the problem, derive the math, write the code, run the test, keep the artifact.
- It integrates with agents via npx skills add rohitg00/ai-engineering-from-scratch: Claude, Cursor, Codex, or any SKILL.md-compatible agent acts as a tutor with placement quizzes and personalized paths in your terminal.
- The site claims readers from Apple, Google, Meta, OpenAI, and NVIDIA.
More from coding & agent
- Hermes ships subagent routes plugin for per-task model orchestration — intellectronica · 2026-10-25
- Claude drives ComfyUI for hours, auto-generates ~500 varied Kromoss images — hazadaza · 2026-10-25
- How LLM-based penetration testing harnesses work: LLM plans, harness executes — utku1337 · 2026-10-25
- Dev builds a 12MB PvP mini-game that hooks into AI agents to stop idle scrolling — CallumReadIt · 2026-10-25
- Open-source parametric CAD with one interface for AIs and humans, parts by Claude — UnspeakableTruths · 2026-10-25
- EMNLP paper localizes faithfulness and citation errors in agentic deep research systems — EliasEskin · 2026-10-25