# Embeddings are underrated

<https://technicalwriting.dev/ml/embeddings/overview.html>

- Host: [technicalwriting.dev](https://links.thingelstad.xyz/hosts/technicalwriting.dev/)
- Saved: May 15, 2025 (2025-05-15T12:07:37Z)
- Record: https://links.thingelstad.xyz/links/2948b4f635e5/
- JSON: https://links.thingelstad.xyz/links/2948b4f635e5.json

## What Jamie wrote

Good explainer on what embeddings really are. 

> Here’s the mental leap. Embeddings are similar to points on a map. Each number in the embedding array is a dimension, similar to the X-Coordinates and Y-Coordinates from earlier. When an embedding model sends you back an array of 1000 numbers, it’s telling you the point where that text semantically lives in its 1000-dimension space, relative to all other texts. When we compare the distance between two embeddings in this 1000-dimension space, what we’re really doing is figuring out how semantically close or far apart those two texts are from each other.

If you are building custom LLM applications this is likely something you need to use.

## Facts

- Kind: [Page](https://links.thingelstad.xyz/kinds/page/)

## Appears in

- [WT319: Weekly Thing 319 / Embeddings, Passkeys, Macros](https://weekly.thingelstad.com/archive/319/), Notable

## Saved the same week

- [F1 The Movie | Main Trailer - YouTube](https://links.thingelstad.xyz/links/13078ce772a2/) (youtube.com, May 15, 2025)
- [2025-05-11 air traffic control](https://links.thingelstad.xyz/links/204da8961ba5/) (computer.rip, May 15, 2025)
- [Iceland approved the 4-day workweek in 2019: nearly 6 years later, all the predictions made have come true.](https://links.thingelstad.xyz/links/72c62f6e3cac/) (farmingdale-observer.com, May 15, 2025)
- [Creating a static website for all my bookmarks – alexwlchan](https://links.thingelstad.xyz/links/92d31b1394d8/) (alexwlchan.net, May 15, 2025)
- [What is HDR, anyway?](https://links.thingelstad.xyz/links/8f2434a37b44/) (lux.camera, May 15, 2025)

## Elsewhere

- Wayback Machine: https://web.archive.org/web/*/https://technicalwriting.dev/ml/embeddings/overview.html
