↓ Skip to main content
AI & Data

AI on this blog: a reading map

·2 mins
I’ve written about AI and data on and off since 2023, one post at a time. Read in this order, they tell one story: from how machines learn, to how language models work, to building with them, to letting them act.

1. How machines learn
#

PostIn one line
The Core DivideSupervised vs unsupervised learning
K-Nearest NeighborsClassify by the company you keep
Mastering TF-IDFTurning text into numbers that mean something
Data Mining EssentialsDistances, clusters and the core vocabulary
Matrix Multiplication to GPUsWhy AI runs on graphics cards

2. How language models work
#

PostIn one line
GenAIWhat generative AI is, and its building blocks (2023)
Language ModelTransformers and the attention breakthrough
Two Students, Two TalentsAuto-regressive (GPT) vs auto-encoding (BERT) models
The Evolution of Language ModelsFrom 2017’s transformer to today’s families
The Probability EngineThe maths of choosing the next token
Tokens and tokenomicsWhat a token is, context windows, and the bill

3. Building with models
#

PostIn one line
OllamaRunning language models on your own machine
A minimal LangChain + Ollama demoPrompt, model and chain, end to end
A practical RAG assistantAnswering from your own documents
From speech to textSpeech recognition in Python
Choosing the right frameworkThe AI stack, layer by layer
ML pipelines on Vertex AITrain, evaluate and deploy, repeatably

4. Letting models act
#

PostIn one line
From RAG to tools and agentsFunction calling and the agent loop
MCP, the Model Context ProtocolOne standard plug for tools and data
The Ghost BoardA story about agents nobody was watching

The data shelf
#

Analytics and big-data posts that sit underneath much of the above:

Everything tagged AI or data is also collected on the AI & Data topic page.

Author
Samarthya
Engineer, learner, tinkerer. This is my trophy shelf of everyday work and leisure.

Related

AI in practice, part 1: Choosing the right framework

“Which AI framework should I use?” has no single answer, because the names people throw around do completely different jobs. Put them on a map first, and the choice usually makes itself. This series picks up where my earlier posts left off. Those covered the ideas: what generative AI is, how transformers pay attention, why GPUs matter, and two hands-on builds (LangChain with Ollama and a RAG assistant). This part is the map that connects them.