cs/ai.
- AI/ML for Biology & Healthcare: A Learning Path
- Yes you should understand backprop
- HuggingFaceTB
- Deep Learning for Biology: Predicting Protein Functions from Sequences
- The AI water issue is fake
- Part I: how does gradient descent work?
- Writing an LLM from scratch, part 22 -- finally training our LLM!
- Computer Vision: Algorithms and Applications, 2nd ed.
- Evidence that Recent AI Gains are Mostly from Inference-Scaling
- fi-le.net,
- Beyond Orthogonality: How Language Models Pack Billions of Concepts into 12,000 Dimensions
- I built ChatGPT with Minecraft redstone!
- Transformers KV Caching Explained
- GPT-2 Neural Network Poetry
- Prompt Engineering Guide
- Context Engineering for AI Agents: Lessons from Building Manus
- What is a Transformer?
- Learnings from building AI agents
- Building Effective AI Agents
- Building a Linear Regression from Scratch with Python & Mathematics
- The Annotated Kolmogorov-Arnold Network (KAN)
- The Annotated Transformer
- How do LLMs work?
- Large Lambda Model
- A Field Guide to Rapidly Improving AI Products
- The 2025 AI Engineer Reading List
- The Lost Reading Items
- A Deep Dive into the Underlying Architecture of Groq's LPU
- What are 1-bit LLMs?. The Era of 1-bit LLMs with BitNet b1.58 | by Mehul Gupta | Data Science in your pocket | Mar, 2024 | Medium
- A Visual Guide to Vision Transformers | MDTURP
- Ilya 30u30
- karpathy/LLM101n: LLM101n: Let's build a Storyteller
- NMI_Review
- Trying Kolmogorov-Arnold Networks in Practice - Casey Primozic's Homepage
- Deep-ML
- Welcome … — Physics-based Deep Learning
- Let's reproduce GPT-2 (1.6B): one 8XH100 node, 24 hours, $672, in llm.c · karpathy/llm.c · Discussion #677
- interdb.jp
- soulmachine/machine-learning-cheat-sheet: Classical equations and diagrams in machine learning
- Ask HN: What are some "toy" projects you used to learn neural networks hands-on? | Hacker News
- A Visual Guide to Quantization - by Maarten Grootendorst
- naklecha/llama3-from-scratch: llama3 implementation one matrix multiplication at a time
- Tensor Labbet · A blog of deep learnings
- How to train a model on 10k H100 GPUs?
- Monty Anderson