Simon Willison’s Weblog

Subscribe

Thursday, 10th August 2023

Release datasette-upload-dbs 0.3 — Upload SQLite database files to Datasette

Getting creative with embeddings (via) Amelia Wattenberger describes a neat application of embeddings I haven’t seen before: she wanted to build a system that could classify individual sentences in terms of how “concrete” or “abstract” they are. So she generated several example sentences for each of those categories, embedded then and calculated the average of those embeddings.

And now she can get a score for how abstract vs concrete a new sentence is by calculating its embedding and seeing where it falls in the 1500 dimension space between those two other points.

# 7:05 pm / ai, generative-ai, llms, embeddings, amelia-wattenberger

TIL Running a Django and PostgreSQL development environment in GitHub Codespaces — Helping people setup development environments (and fix them when they break) can be incredibly frustrating. I'm really excited about cloud-based development environments such as [GitHub Codespaces](https://github.com/features/codespaces) for exactly this reason - I love the idea that you can get a working environment by clicking a green button, and if it breaks you can throw it away and click the button again to get a brand new one.
TIL Catching up with the Cosmopolitan ecosystem — I caught up with some of the latest developments in the ecosystem around Justine Tunney's [cosmopolitan](https://github.com/jart/cosmopolitan) and Actually Portable Executable (APE) projects this week. They are _absolutely fascinating_.
Wednesday, 9th August 2023
Friday, 11th August 2023