Learn

Hands-on AI/ML curriculum, one lesson a day, free.

LLMs & Transformers

How transformer self-attention actually works, with a runnable toy

11/07/2026
Tokenization pitfalls: why your LLM miscounts characters and money

12/07/2026
Context windows, KV-cache, and why long prompts get expensive

15/07/2026
Fine-tuning vs LoRA vs prompting: choosing the cheapest path that works

05/08/2026

RAG & Agentic Development

Build a minimal RAG pipeline: chunk, embed, retrieve, answer

11/07/2026
Chunking strategies that actually matter for retrieval quality

13/07/2026
Choosing a vector database in 2026: pgvector vs the specialists

16/07/2026
Hybrid search: combining BM25 keyword and dense vectors

05/08/2026

Computer Vision

Object detection today: from YOLO to open-vocabulary models

11/07/2026
Image segmentation with Segment Anything and its successors

15/07/2026
How diffusion models generate images, explained with a runnable toy

17/07/2026
Vision-language models: teaching an LLM to see

06/08/2026

ML Foundations & Chatbots

The bias-variance tradeoff, finally explained with runnable plots

11/07/2026
Data leakage: the silent killer of ML projects

14/07/2026
Feature stores and reproducible training pipelines

30/07/2026
Model monitoring in production: drift, decay, and alerting

06/08/2026