Tag
A repository that builds a GPT-style transformer from scratch without high-level libraries, covering everything from data preprocessing to generation, and includes guides for SFT and RLHF.
Built an MCP server allowing Claude to control NetLogo for agent-based modeling, including headless sweeps and model loading from CoMSES Net.
AgentSwarms launched 67 free, TypeScript-based interactive notebooks for learning multi-agent systems, covering LangChain fundamentals to production-grade error handling and failure modes.
Introduces the Machine Learning Visualized project on GitHub. This tool uses interactive notebooks and visualizations to show the training process of machine learning algorithms (e.g., neural networks, logistic regression, etc.), helping beginners understand the principles.
The author built Joey, a 170M parameter masked diffusion language model from scratch, trained on FineWeb-Edu and fine-tuned on DailyDialog, achieving fluent but incoherent sentences due to capacity limitations. The project highlights the differences from autoregressive LLMs and the lessons learned from building and debugging the system.
A hands-on tutorial series that bridges the gap between understanding async Rust internals (Future, poll, Pin, executor) and shipping real async code with Tokio, aimed at developers familiar with JavaScript async and basic Rust.
A Twitter thread listing 35 essential system design concepts with links to detailed explanations, aimed at helping developers learn and review key topics.
A detailed walkthrough of how transformer-based LLMs work, covering tokenization, embeddings, attention, and next-token prediction without heavy math.
This blog post explains Large Reasoning Models (LRMs), how they differ from standard LLMs, their training, and when to use them. It covers examples like DeepSeek R1 and GPT-5.5 Thinking.
A tweet curating foundational resources for understanding modern AI, covering topics from transformers to physical AI, including key papers and models.
CMU Software Engineering Institute publishes an overview of ML training infrastructure, covering hardware considerations like GPU vs CPU and memory requirements.
A free learning guide on Agentic AI designed for high school students, available as a PDF on Google Drive.
A structured course built from personal study notes of the book *Linux Basics for Hackers* by OccupyTheWeb, covering core Linux concepts and commands for cybersecurity beginners.
KL Zero is an interactive browser game where players draw a probability distribution to match a target KL divergence value, helping users intuitively understand the concept of KL divergence in machine learning.
A glossary from TechCrunch that defines common AI terms such as AGI, AI agents, API endpoints, and chain of thought, updated regularly as the field evolves.
An interactive visual guide explaining the Constant-Q Transform (CQT), its log-frequency geometry, comparison with FFT, kernel construction, and efficient computation, tailored for music and pitch analysis.
An interactive visual guide that explains how large language models work, from tokenization through attention, transformer blocks, and text generation, built by Roy van Rijn.
An interactive web-based tool that visualizes 24 algorithms step-by-step, covering pathfinding, sorting, recursion, and more, built with React.
A curated video-guided curriculum and comprehensive list of resources for learning ML systems and LLM infrastructure, including papers, courses, and tutorials.
Hugging Face offers a deep reinforcement learning course with practical exercises, now in low-maintenance state but still a useful resource for learning theory and hands-on DRL.