zero to ai-native
an open-source curriculum of primary-source ai material.
straight from the people building it. grouped by level, so you always know what to read next.
116 reads · 31 sources
scroll for more →
intro
28Identifying and Scaling AI Use Cases
AI in the Enterprise
The State of Enterprise AI 2025
Building Trusted AI in the Enterprise
How AI Is Transforming Work at Anthropic
Prompt Engineering
Foundational LLMs & Text Generation
Gemini for Workspace Prompting Guide 101
AI Agents for Beginners
Generative AI for Beginners
Prompt Engineering Interactive Tutorial
Gemini (whitepaper)
Llama Responsible Use Guide
DeepSeek-R1 Usage Recommendations
LLM University (LLMU)
AI Agents Course
LLM Course
Neural Networks: Zero to Hero
Deep Dive into LLMs like ChatGPT
Software 2.0
CS229: Machine Learning
6.S191: Introduction to Deep Learning
AI Eats the World
The Illustrated Transformer
Neural Networks
Machines of Loving Grace
Policy on the AI Exponential
The Intelligence Age
build
37A Practical Guide to Building Agents
From Experiments to Deployments
GPT-5 Prompting Guide
GPT-4.1 Prompting Guide
Evaluation Best Practices
The Complete Guide to Building Skills for Claude
Building Effective AI Agents
Building Effective Agents (essay)
Project Vend: Phase Two
Project Deal
Writing Effective Tools for Agents
5-Day Gen AI Intensive
Agents
Gemini Enterprise Prompt Guide
MCP Introduction
Llama Prompting Guide
Prompting Capabilities
Smol Course
Context Rot: How Input Length Hurts LLM Performance
Evaluating Chunking Strategies for Retrieval
Generative Benchmarking
LLM Powered Autonomous Agents
Prompt Engineering (In-Context Prompting)
Why We Built Our Own Background Agent
How To Build Agents Users Can Trust
How Ramp Fixes Merchant Matches with AI
Patterns for Building LLM-based Systems & Products
What We Learned from a Year of Building with LLMs
Your AI Product Needs Evals
A Field Guide to Rapidly Improving AI Products
Building LLM Applications for Production
CS224N: NLP with Deep Learning
State of LLMs 2025
Useful Patterns for Building HTML Tools
Prompt Injection Explained
Using LLMs to Help Me Write Code
Agents (Chip Huyen)
deep
51o1 System Card
OpenAI Model Spec
Practices for Governing Agentic AI Systems
Model Disproves the Erdős Unit Distance Conjecture
Fine-tuning Best Practices
Separating Signal from Noise in Coding Evaluations
GPT-5.6 System Card
Scaling Laws for Neural Language Models
Language Models are Few-Shot Learners (GPT-3)
Training Language Models to Follow Instructions (InstructGPT)
Claude Code: Best Practices for Agentic Coding
Effective Context Engineering for AI Agents
When AI Builds Itself
Exploring Model Welfare
Anthropic Economic Index: Economic Primitives
Anthropic Economic Index: Geographic & Enterprise Adoption
Agents Companion
Generative AI Lens (Well-Architected)
Claude's Constitution
Alignment Faking in Large Language Models
An Off Switch for Dual-Use Knowledge in AI Models
Gemini 3 Pro Frontier Safety Framework Report
Gemini Achieves IMO Gold Medal
AlphaGeometry2
M
Kimi K3: Open Frontier Intelligence
M
PerceptionBench
M
How We Scaled Kimi K2.5
Deep RL Course
Attention Is All You Need
Chain-of-Thought Prompting Elicits Reasoning
Training Compute-Optimal LLMs (Chinchilla)
LLaMA: Open and Efficient Foundation Language Models
Retrieval-Augmented Generation (RAG)
LoRA: Low-Rank Adaptation of Large Language Models
Constitutional AI: Harmlessness from AI Feedback
Mixtral of Experts
Mistral 7B
DeepSeek-R1: Incentivizing Reasoning via RL
DeepSeek-V3 Technical Report
YaRN: Efficient Context Window Extension
Qwen2.5 Technical Report
Extrinsic Hallucinations in LLMs
Reward Hacking in Reinforcement Learning
CS336: Language Modeling from Scratch
CS25: Transformers United
The Economics of Transformative AI
CS153: Frontier Systems
MS&E435: Economics of the AI Supercycle
The Adolescence of Technology
Situational Awareness: The Decade Ahead