--- title: "Articles" description: "Longform explainers and essays on AI research topics — curated writing for people learning the field seriously." canonical_url: "https://fanout.sh/ai/articles" md_url: "https://fanout.sh/ai/articles.md" access: "public" --- # Articles Longform explainers and essays on AI research topics — curated writing for people learning the field seriously. ## Articles ### [The Illustrated Transformer](https://jalammar.github.io/illustrated-transformer/) The best visual explanation of how transformers work. Essential reading before building one. - Author: Jay Alammar - Category: Tutorials ### [Attention Is All You Need (Annotated)](https://nlp.seas.harvard.edu/annotated-transformer/) The original transformer paper, annotated with working PyTorch code line by line. - Author: Harvard NLP - Category: Tutorials ### [The Illustrated GPT-2](https://jalammar.github.io/illustrated-gpt2/) Visual walkthrough of GPT-2's architecture — how autoregressive language models generate text. - Author: Jay Alammar - Category: Tutorials ### [A Recipe for Training Neural Networks](https://karpathy.github.io/2019/04/25/recipe/) Practical tips for training neural networks. The most shared ML blog post ever. - Author: Andrej Karpathy - Category: Guides ### [Yes You Should Understand Backprop](https://karpathy.medium.com/yes-you-should-understand-backprop-e2f06eab496b) Why understanding backpropagation matters. Don't just use autograd blindly. - Author: Andrej Karpathy - Category: Insights ### [The Bitter Lesson](http://www.incompleteideas.net/IncIdeas/BitterLesson.html) The most important essay in AI. General methods + compute always win over human knowledge. - Author: Rich Sutton - Category: Insights ### [Scaling Laws for Neural Language Models](https://arxiv.org/abs/2001.08361) How LLM performance scales with data, compute, and model size. Foundation of modern scaling. - Author: Kaplan et al. (OpenAI) - Category: Papers ### [An Introduction to LLMs](https://lilianweng.github.io/posts/2023-06-23-agent/) Comprehensive blog covering LLM training, RLHF, prompting, and emergent abilities. - Author: Lilian Weng - Category: Guides ### [Neural Networks: Zero to Hero](https://karpathy.ai/zero-to-hero.html) Full video course building neural networks from scratch in Python. The GOAT free course. - Author: Andrej Karpathy - Category: Tutorials ### [What Is ChatGPT Doing?](https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work/) Deep, intuitive explanation of how LLMs work. Great for building mental models. - Author: Stephen Wolfram - Category: Insights ### [The Illustrated Word2Vec](https://jalammar.github.io/illustrated-word2vec/) Visual guide to word embeddings. How words become vectors that capture meaning. - Author: Jay Alammar - Category: Tutorials ### [Understanding LSTM Networks](https://colah.github.io/posts/2015-08-Understanding-LSTMs/) The clearest explanation of LSTMs ever written. Beautiful diagrams, perfect intuition. - Author: Chris Olah - Category: Tutorials ### [Chinchilla Scaling Laws](https://arxiv.org/abs/2203.15556) Compute-optimal training — most LLMs are undertrained. Changed how labs scale models. - Author: Hoffmann et al. (DeepMind) - Category: Papers ### [The AI Revolution: The Road to Superintelligence](https://waitbutwhy.com/2015/01/artificial-intelligence-revolution-1.html) The most accessible introduction to where AI is heading. Changed how millions think about AI. - Author: Tim Urban (Wait But Why) - Category: Insights ### [How to Read a Paper](https://web.stanford.edu/class/ee384m/Handouts/HowtoReadPaper.pdf) Three-pass approach to reading research papers efficiently. Essential skill for researchers. - Author: S. Keshav - Category: Guides ### [Practical Tips for Fine-Tuning LLMs](https://magazine.sebastianraschka.com/p/practical-tips-for-finetuning-llms) Concrete advice on LoRA, QLoRA, data preparation, and evaluation for fine-tuning. - Author: Sebastian Raschka - Category: Guides ### [Understanding and Coding Self-Attention from Scratch](https://sebastianraschka.com/blog/2023/self-attention-from-scratch.html) Step-by-step implementation of the self-attention mechanism in PyTorch. The clearest code-first attention tutorial. - Author: Sebastian Raschka - Category: Tutorials ### [A Visual Guide to Attention Variants in Modern LLMs](https://magazine.sebastianraschka.com/p/visual-attention-variants) Comprehensive visual exploration of MHA, GQA, MLA, sparse attention, and hybrid architectures used in modern LLMs. - Author: Sebastian Raschka - Category: Tutorials ### [Understanding Reasoning LLMs](https://magazine.sebastianraschka.com/p/understanding-reasoning-llms) Four main approaches to building reasoning-enhanced models — inference-time scaling, RLVR, and beyond. - Author: Sebastian Raschka - Category: Guides ### [Improving LoRA: Implementing DoRA from Scratch](https://magazine.sebastianraschka.com/p/lora-and-dora-from-scratch) The LoRA successor — Weight-Decomposed Low-Rank Adaptation explained and implemented in code. - Author: Sebastian Raschka - Category: Tutorials ### [Components of a Coding Agent](https://magazine.sebastianraschka.com/p/components-of-a-coding-agent) How coding agents work — tools, memory, and repository context for LLM-based agents. (Apr 2026) - Author: Sebastian Raschka - Category: Guides ### [The State of LLMs 2025](https://magazine.sebastianraschka.com/p/state-of-llms-2025) Annual review covering DeepSeek R1, RLVR, benchmarks, open-weight progress, and 2026 predictions. - Author: Sebastian Raschka - Category: Insights ### [Understanding Multimodal LLMs](https://magazine.sebastianraschka.com/p/understanding-multimodal-llms) Techniques and latest models in vision-language integration — how LLMs learn to see. - Author: Sebastian Raschka - Category: Guides ### [Gradient Descent Visualized](https://lilianweng.github.io/posts/2017-10-15-gradient/) Visual guide to optimization algorithms — SGD, Momentum, Adam, and beyond. - Author: Lilian Weng - Category: Tutorials ### [The Unreasonable Effectiveness of RNNs](https://karpathy.github.io/2015/05/21/rnn-effectiveness/) Classic blog showing what RNNs can learn — Shakespeare, code, Wikipedia, math. - Author: Andrej Karpathy - Category: Insights ### [LLM Evaluation: 4 Approaches from Scratch](https://sebastianraschka.com/blog/2025/llm-evaluation-4-approaches.html) Multiple-choice benchmarks, verifiers, leaderboards, and LLM judges — all with from-scratch code examples. The complete evaluation toolkit. - Author: Sebastian Raschka - Category: Tutorials ### [LLM Architecture Gallery](https://sebastianraschka.com/blog/2026/llm-architecture-gallery.html) Visual gallery of 40+ LLM architectures (Llama, DeepSeek, Qwen, Gemma) with clickable diagrams, fact sheets, and concept explainers for GQA, MLA, and more. - Author: Sebastian Raschka - Category: Guides ### [Defeating Nondeterminism in LLM Inference](https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/) Why LLMs give different outputs even at temperature=0 — and an open-source PyTorch library for 100% bitwise-identical outputs. Essential for production reliability. - Author: Thinking Machines Lab - Category: Papers ### [Context Engineering is the New Skill](https://www.philschmid.de/context-engineering) Why context engineering has replaced prompt engineering as the key skill — how to structure inputs for agents, not just chat. - Author: Phil Schmid - Category: Insights ### [Getting the Most Out of Claude Code 2.0](https://sankalp.bearblog.dev/my-experience-with-claude-code-20-and-how-to-get-better-at-using-coding-agents/) The most bookmarked guide (20K bookmarks) on working with AI coding agents. Practical workflows and best practices from extensive real-world usage. - Author: Sankalp (dejavucoder) - Category: Guides ### [Perplexity's 42-Page Internal AI at Work Guide](https://www.perplexity.ai/hub/blog/ai-at-work-getting-more-done-with-less-hype) How a top AI company actually uses AI internally — email automation, meeting prep, research amplification. 21K bookmarks. Real playbook, not theory. - Author: Perplexity AI - Category: Guides ### [300+ ML System Design Case Studies](https://github.com/Engineer1999/A-Curated-List-of-ML-System-Design-Case-Studies) Battle-tested ML system designs from 80+ companies (Netflix, Spotify, Uber, Stripe). The best resource for understanding how ML works in production. - Author: Engineer1999 - Category: Guides ### [Building a Vector Database from First Principles](https://x.com/archiexzzz/status/1985015166816153852) From-scratch implementation with linear scan, KD-tree, HNSW, and IVF indexes. Understand how vector search actually works under the hood. - Author: Archie Sengupta - Category: Tutorials ### [SWE-CI: Why AI Coding Agents Fail at Long-Term Maintenance](https://arxiv.org/abs/2603.03823) First benchmark testing AI agents across 233-day maintenance windows. 75% of models break previously working code. Only Claude Opus stays above 50%. - Author: Sun Yat-sen University & Alibaba - Category: Papers --- This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included. Browse the public content map: https://fanout.sh/sitemap.md