---
date: "2024-05-17T19:02:25.000Z"
title: "2024-05-17"
tags: ["gpt-4o","datasette","language_models"]
draft: false
---

Sabrina wrote an interesting
[write up](https://www.sabrina.dev/p/chatgpt4o-vs-math) on solving a math
problem with `gpt-4o`. It turned out the text-only, chain-of-thought approach
was the best performing, which is not what I would have guessed.

It's was cool to see Simon dive into LLM-driven data extraction in using his
project `datasette` in
[this video](https://www.youtube.com/watch?v=g3NtJatmQR0). Using multi-modal
models for data extraction seems to bring a new level of usefulness and makes
these models even more general purpose.