30u30
A study guide for learning 30 foundational AI papers through hands-on implementations, notes, and exercises. It helps readers connect paper ideas to working deep-learning concepts one paper at a time.
Share on XCustom license (see repository)
Overview
30u30 is an open-source study guide for learning foundational AI research through a one-paper-per-day path centered on 30 papers recommended by Ilya Sutskever. It helps bridge the gap between reading a paper and understanding how its ideas work by pairing papers with from-scratch implementations, notes, interactive exercises with solutions, and visualizations. Learners follow the sequence, study each paper and its math, then work through the implementation and exercises.
Key features
- A guided sequence covering 30 foundational AI papers, one per day
- From-scratch implementations, including a character-level RNN and an LSTM
- Interactive exercises with solutions for each paper
- Notes and visualizations to support understanding
Best for
Learners who want a structured path through foundational AI papers and prefer to explore ideas by implementing them and completing exercises.
- Upstream
- Ojhaharsh/30u30
- Fork on GitHub
- Guo-astro/30u30
- Upstream stars
- 588
- Category
- Learning, interviews and curated lists
- Language
- Python
- License
- Custom license (see repository)
- Forked
- 2026-10-16
- Sync status
- In syncLast synced 2026-10-17
More in Learning, interviews and curated lists
A personal collection of ML systems learning notes, focused on RL infrastructure, inference systems, and AI infrastructure fundamentals for readers studying how these systems work.
Forked 2026-10-17Last synced 2026-10-17License: Apache-2.0Learning, interviews and curated listsGitHub
A system design learning repository that gathers case studies, interview resources, a design template, and guidance for studying and practicing system design.
Forked 2026-10-14Last synced 2026-10-17License: MITLearning, interviews and curated listsGitHub
A concise introduction to reinforcement learning, from fundamentals to applied algorithms. Use the book to learn the subject and its PyTorch examples and supplementary proofs to study key methods in more detail.
Forked 2026-10-14Last synced 2026-10-17No license declaredLearning, interviews and curated listsGitHub
A curated directory of Telegram resources for discovering bots, groups, channels, tools, and development libraries. Use it to find services and references across the Telegram ecosystem.
Forked 2026-10-12Last synced 2026-10-17No license declaredLearning, interviews and curated listsGitHub