ML & AI

Machine learning, deep learning, LLMs & building AI applications

BuddingMar 17, 2026·32 min read

Build an LLM Playground — Part 1: How Large Language Models Actually Work

The first entry in a learn-by-doing series to become an AI engineer. We break down every stage of how LLMs are built — from raw data to chatbot — so you can build your own playground with real understanding.

aillmmachine-learningtransformersdeep-learningtutorialseries
BuddingMar 17, 2026·34 min read

Build an LLM Playground — Part 2: Build a Customer Support Chatbot using RAGs and Prompt Engineering

The second entry in the learn-by-doing AI engineer series. We cover adaptation techniques, prompt engineering strategies, and a full deep-dive into Retrieval-Augmented Generation — from document parsing to evaluation — so you can build a customer support chatbot grounded in real knowledge.

aillmragprompt-engineeringchatbotembeddingsvector-searchtutorialseries
BuddingMar 17, 2026·40 min read

Build an LLM Playground — Part 4: Build "Deep Research" with Web Search and Reasoning Models

The fourth entry in the learn-by-doing AI engineer series. We cover reasoning and thinking LLMs, inference-time scaling techniques (CoT, self-consistency, Tree of Thoughts), training-time techniques (STaR, RLHF with verifiers, reward modeling), and build a deep research agent that combines web search with multi-step reasoning.

aillmreasoningchain-of-thoughtdeep-researchtree-of-thoughtsreinforcement-learningtutorialseries
BuddingMar 17, 2026·44 min read

Build an LLM Playground — Part 5: Build a Multi-modal Generation Agent

The fifth entry in the learn-by-doing AI engineer series. We cover the full landscape of visual generation — VAEs, GANs, auto-regressive models, and diffusion models — then go deep on text-to-image and text-to-video pipelines, and build a multi-modal generation agent.

aidiffusiontext-to-imagetext-to-videostable-diffusionvaegandittutorialseries
EvergreenMar 16, 2026·26 min read

The Complete ML & AI Learning Roadmap — With Code

A hands-on, code-first guide to learning machine learning and AI. Every concept comes with runnable Python code you can copy-paste and execute. Start from scratch, build real things, and prepare for ML interviews.

machine-learningdeep-learningaillmroadmapinterviewspythonpytorch