34 must-read engineering posts, tutorials, and breakthroughs.
by Jay Alammar
The best visual explanation of how transformers work. Essential reading before building one.
by Harvard NLP
The original transformer paper, annotated with working PyTorch code line by line.
by Jay Alammar
Visual walkthrough of GPT-2's architecture — how autoregressive language models generate text.
by Andrej Karpathy
Practical tips for training neural networks. The most shared ML blog post ever.
by Andrej Karpathy
Why understanding backpropagation matters. Don't just use autograd blindly.
by Rich Sutton
The most important essay in AI. General methods + compute always win over human knowledge.
by Kaplan et al. (OpenAI)
How LLM performance scales with data, compute, and model size. Foundation of modern scaling.
by Lilian Weng
Comprehensive blog covering LLM training, RLHF, prompting, and emergent abilities.
by Andrej Karpathy
Full video course building neural networks from scratch in Python. The GOAT free course.
by Stephen Wolfram
Deep, intuitive explanation of how LLMs work. Great for building mental models.
by Jay Alammar
Visual guide to word embeddings. How words become vectors that capture meaning.
by Chris Olah
The clearest explanation of LSTMs ever written. Beautiful diagrams, perfect intuition.
by Hoffmann et al. (DeepMind)
Compute-optimal training — most LLMs are undertrained. Changed how labs scale models.
by Tim Urban (Wait But Why)
The most accessible introduction to where AI is heading. Changed how millions think about AI.
by S. Keshav
Three-pass approach to reading research papers efficiently. Essential skill for researchers.
by Sebastian Raschka
Concrete advice on LoRA, QLoRA, data preparation, and evaluation for fine-tuning.
by Sebastian Raschka
Step-by-step implementation of the self-attention mechanism in PyTorch. The clearest code-first attention tutorial.
by Sebastian Raschka
Comprehensive visual exploration of MHA, GQA, MLA, sparse attention, and hybrid architectures used in modern LLMs.
by Sebastian Raschka
Four main approaches to building reasoning-enhanced models — inference-time scaling, RLVR, and beyond.
by Sebastian Raschka
The LoRA successor — Weight-Decomposed Low-Rank Adaptation explained and implemented in code.
by Sebastian Raschka
How coding agents work — tools, memory, and repository context for LLM-based agents. (Apr 2026)
by Sebastian Raschka
Annual review covering DeepSeek R1, RLVR, benchmarks, open-weight progress, and 2026 predictions.
by Sebastian Raschka
Techniques and latest models in vision-language integration — how LLMs learn to see.
by Lilian Weng
Visual guide to optimization algorithms — SGD, Momentum, Adam, and beyond.
by Andrej Karpathy
Classic blog showing what RNNs can learn — Shakespeare, code, Wikipedia, math.
by Sebastian Raschka
Multiple-choice benchmarks, verifiers, leaderboards, and LLM judges — all with from-scratch code examples. The complete evaluation toolkit.
by Sebastian Raschka
Visual gallery of 40+ LLM architectures (Llama, DeepSeek, Qwen, Gemma) with clickable diagrams, fact sheets, and concept explainers for GQA, MLA, and more.
by Thinking Machines Lab
Why LLMs give different outputs even at temperature=0 — and an open-source PyTorch library for 100% bitwise-identical outputs. Essential for production reliability.
by Phil Schmid
Why context engineering has replaced prompt engineering as the key skill — how to structure inputs for agents, not just chat.
by Sankalp (dejavucoder)
The most bookmarked guide (20K bookmarks) on working with AI coding agents. Practical workflows and best practices from extensive real-world usage.
by Perplexity AI
How a top AI company actually uses AI internally — email automation, meeting prep, research amplification. 21K bookmarks. Real playbook, not theory.
by Engineer1999
Battle-tested ML system designs from 80+ companies (Netflix, Spotify, Uber, Stripe). The best resource for understanding how ML works in production.
by Archie Sengupta
From-scratch implementation with linear scan, KD-tree, HNSW, and IVF indexes. Understand how vector search actually works under the hood.
by Sun Yat-sen University & Alibaba
First benchmark testing AI agents across 233-day maintenance windows. 75% of models break previously working code. Only Claude Opus stays above 50%.