---
title: "Similarity With Dot Product"
description: "Score vectors with a dot product, see how a longer vector can win without matching direction, and how cosine similarity divides the length out."
canonical_url: "https://fanout.sh/ai/lessons/core-ai-intuitions-similarity-dot-product"
md_url: "https://fanout.sh/ai/lessons/core-ai-intuitions-similarity-dot-product.md"
access: "pro-preview"
---

# Similarity With Dot Product

Score vectors with a dot product, see how a longer vector can win without matching direction, and how cosine similarity divides the length out.

- Access: Fanout Pro (public preview)
- Module: Core AI Intuitions

## A glimpse of Similarity With Dot Product

Suppose we describe a movie with two chosen numbers: action content, then comedy content. A viewer's preference is u = [1, 0], so our tiny scoring rule rewards action and ignores comedy. These are invented features for this example, not measurements from a recommendation system.

Movie A has features [1, 0]. Movie B has [2, 2].

## Continue learning

Pro unlocks guided learning, complete notes, practical walkthroughs, exercises, and every AI Research lesson.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md