Layer by Layer

This blog is all about me learning in public and sharing what I discover along the way. If something I write helps even one person understand a concept better, I’ll consider this blog a success.

Coding Agents: AI Driven Dev Conference

AI

Software Engineering

Coding Agents

Events

I am trying to make better use of all the meetups, conferences, startup events, and overall the energy and excitement in the Bay Area - in particular around agentic AI and…

Project Second Brain

Productivity

Learning

Centralized Knowledge Base

I’ve recently posted about automating some of my daily work that’s not directly software engineering (mostly project management-related tasks, see my Obsidian note-taking…

LLM-Powered Work Notes: How I Use Obsidian and Cursor to Capture Everything

Productivity

Note-Taking

Overall, I am always looking for ways to automate the repetitive tasks and busywork of my day-to-day work. In this post, I describe my attempt at building a note-taking…

The Curious World of MCP Servers

MCP

Productivity

Using AI assistants for software engineering has practically become non-optional for tech workers. At NVIDIA, I routinely use AI assistants for software engineering - to the…

OpenAI Dev Day 2025 Recap

OpenAI

Dev Day

After a full day of talks, demos, and AMAs I just wanted to provide a little more color and detail about Open AI’s dev day 2025. I did not exactly know what to expect from…

Robust Autonomy Emerges from Self-Play

paper-review

autonomous-driving

A few weeks ago I came across a paper titled “Robust Autonomy Emerges from Self-Play” in the TLDR newsletter (which is worth subscribing to if you want to stay on top of the…

LLMs From Scratch - Chapter 7: Fine-tuning for Instruction Following

llms

fine-tuning

tutorial

This notebook explores the fine-tuning process of LLMs with the purpose of creating instruction fine-tuned model based on Sebastian Raschka’s book (Chapter 7). In…

LLMs From Scratch - Chapter 6: Fine-tuning for Classification

llms

fine-tuning

tutorial

This notebook explores the fine-tuning process of LLMs with the purpose of creating a classification model based on Sebastian Raschka’s book (Chapter 6). In particular, it…

LLMs From Scratch - Chapter 5: Pretraining from Unlabeled Data

llms

tutorial

This notebook explores pretraining process of LLMs based on Sebastian Raschka’s book (Chapter 5). In particular, it discusses the following:

LLMs From Scratch - Chapter 4: GPT from Scratch

llms

gpt

tutorial

This notebook explores full LLM architecture for GPT based on Sebastian Raschka’s book (Chapter 4), implementing normalization layers, shortcut connections, and transformer…

LLMs From Scratch - Chapter 3: Attention Mechanisms

llms

attention

tutorial

This notebook explores attention mechanisms (including self-attention) based on Sebastian Raschka’s book (Chapter 3), implementing basic self-attention, causal…

LLMs From Scratch - Chapter 2: Dataloader Creation

llms

dataloader

tutorial

This notebook explores dataset/dataloader creation techniques based on Sebastian Raschka’s book (Chapter 2), implementing data sampling, batching, and other techniques.

LLMs From Scratch - Chapter 1: Tokenization

llms

pretraining

tutorial

Tokenization is a fundamental process in Natural Language Processing (NLP) that involves breaking text into smaller units called “tokens.” These tokens serve as the basic…

Build a Large Language Model (From Scratch)

LLMs

I recently finished reading (or rather working through) my technical book of the month - Build a Large Language Model (From Scratch) by Sebastian Raschka and wanted to share…

Tech Stack for This Website

website

For the longest time I have been hosting some version of my website using WordPress, which was the style at the time (this is 2012 onwards but pre-ChatGPT). While I really…

Welcome to Layer by Layer

news

introduction

Hello and welcome to Layer by Layer - and experiment in learning in public where I’ll be sharing my exploration of machine learning concepts, techniques, and research.