Embeddings — LLMs Part 5
The Definition An embedding is a list of numbers that represents one token’s meaning. That list is also called a vector — an ordered list of numbers, nothing more. Here meaning has a narrow sense...
Sachin Joseph — Notes on code, tools, and whatever I'm currently digging into.
Paper: Byte Pair Encoding — LLMs Part 4
Sennrich, Haddow & Birch, “Neural Machine Translation of Rare Words with Subword Units” (2015) The Problem A model with a fixed vocabulary (Part 3) can’t handle a word it has never seen — a m...
Tokens, Not Words — LLMs Part 3
The Definition A token is the actual unit a language model reads and predicts. It is not always a word. It can be a whole word, part of a word, or a single punctuation mark. Before a model is tra...
What a Neural Network Actually Is — LLMs Part 2
The Definition A neural network is a function: it takes in numbers and produces numbers out. Each number going in is called an input — nothing more than a plain number. A network might take two in...
What Is a Language Model? — LLMs Part 1
The Definition A language model is a neural network trained to do one thing: given some text, predict what comes next. We’ll define a neural network in Part 2. For now, think of it as a program th...
Configure PowerShell autocomplete using PSReadLine
Improving the PowerShell editing experience can greatly improve your productivity. PSReadLine, in a line, is a PowerShell module that does just that - it provides improved syntax coloring, better m...
Search Open Browser Tabs
TL;DR: On Chromium-based browsers like Edge and Chrome, press Ctrl+Shift+A. On Firefox, press Ctrl+L (or Alt+D) to focus on the address bar, then type % and then tap the Spacebar. I have a ...
Windows Sandbox: Run unknown apps confidently
Running unknown apps is risky: Not immediately obvious what a program does. Unintended side effects (change the file system, send emails, etc.) Resource intensive, slow startup, blocking I/...