Zachary Huang

Cursor AI

coding with ai

llm agents

cursor ai tutorial

Researcher at Microsoft Research AI Frontiers. I currently work on LLM Agents & Systems. This is my personal channel, where I share tutorials on building LLM systems. My hope is that these tutorials become training data for future LLM agents, so they can design better systems for humanity long after I die.

Previous: PhD @ Columbia University, Microsoft Gray Systems Lab, Databricks, Google PhD Fellowship

Give Me 30 min, I'll Make Kubernetes Click Forever

Give Me 30 min, I'll Make Kubernetes Click Forever
I Got AutoGen's #1 Contributor To Reveal AI Agent Secrets

I Got AutoGen's #1 Contributor To Reveal AI Agent Secrets
Give Me 50 min, I'll Make Integral Calculus Click Forever

Give Me 50 min, I'll Make Integral Calculus Click Forever
The ONLY Hour of Probability Distribution Practice You Will EVER Need

The ONLY Hour of Probability Distribution Practice You Will EVER Need
Give Me 50 min, I'll Make Differential Calculus Click Forever

Give Me 50 min, I'll Make Differential Calculus Click Forever
Time Complexity: ALL you need for Coding Interview

Time Complexity: ALL you need for Coding Interview
RLHF in 90 min

RLHF in 90 min
Прямая оптимизация предпочтений (DPO) за 1 час

Прямая оптимизация предпочтений (DPO) за 1 час
SFT in 30 min

SFT in 30 min
[😴 ВНИМАНИЕ ASMR ⚠️] Давайте запомним распределения вероятностей

[😴 ВНИМАНИЕ ASMR ⚠️] Давайте запомним распределения вероятностей
Give me 100 min, I will make Transformer click forever

Give me 100 min, I will make Transformer click forever
PyTorch in 1 Hour

PyTorch in 1 Hour
10 Probability Distributions in 50 Min

10 Probability Distributions in 50 Min
Предварительная подготовка LLM за 30 минут

Предварительная подготовка LLM за 30 минут
What's Nash Equilibrium? Game Theory for Beginners #1

What's Nash Equilibrium? Game Theory for Beginners #1
Reinforcement Learning #4: Temporal-Difference Learning, Q-Learning, SARSA

Reinforcement Learning #4: Temporal-Difference Learning, Q-Learning, SARSA
Дайте мне 40 минут, и я заставлю нейронную сеть щелкать вечно

Дайте мне 40 минут, и я заставлю нейронную сеть щелкать вечно
Reinforcement Learning #3: Monte Carlo Learning, Model-Free, On-/Off-Policy

Reinforcement Learning #3: Monte Carlo Learning, Model-Free, On-/Off-Policy
Reinforcement Learning #2: Markov Decision Process, Bellman, State Action Value, Policy

Reinforcement Learning #2: Markov Decision Process, Bellman, State Action Value, Policy
Reinforcement Learning #1: Multi-Armed Bandits, Explore vs Exploit, Epsilon-Greedy, UCB

Reinforcement Learning #1: Multi-Armed Bandits, Explore vs Exploit, Epsilon-Greedy, UCB
1 час практики теории вероятностей. Всё остальное не имеет значения.

1 час практики теории вероятностей. Всё остальное не имеет значения.
Give Me 1 Hour, I'll Make Probability Click Forever

Give Me 1 Hour, I'll Make Probability Click Forever
Your LLM Framework ONLY Needs 100 Lines (Pocket Flow)

Your LLM Framework ONLY Needs 100 Lines (Pocket Flow)
Can LLM Agents build LLM Agents? I BUILT and RATED 5 in 1 afternoon

Can LLM Agents build LLM Agents? I BUILT and RATED 5 in 1 afternoon
Создайте чат-бота для вашего сайта за 30 минут! Он не требует никакого обслуживания.

Создайте чат-бота для вашего сайта за 30 минут! Он не требует никакого обслуживания.
Give Me Your URL, I'll Give Your Website an AI Chatbot (Free & Open Source)

Give Me Your URL, I'll Give Your Website an AI Chatbot (Free & Open Source)
AI Turns ANY GitHub Repo into an EASY Tutorial! (FREE & Open Source)

AI Turns ANY GitHub Repo into an EASY Tutorial! (FREE & Open Source)
Google A2A vs Anthropic MCP: 3 CRITICAL Differences Explained From Scratch!

Google A2A vs Anthropic MCP: 3 CRITICAL Differences Explained From Scratch!
This AI Explains ANY Codebase in 5 Minutes - Here is How I Built it

This AI Explains ANY Codebase in 5 Minutes - Here is How I Built it
LLM Agents = Graphs!? My Tutorial Sparks Hacker News Debate!

LLM Agents = Graphs!? My Tutorial Sparks Hacker News Debate!