Simon Willison simonw

Explaining the code from fastest-levenshtein

Starting with this code: https://github.com/ka-weihe/fastest-levenshtein/blob/master/mod.ts

I asked:

Explain this code:

Explaining mathematical expressions with GPT-3

I wanted to see if GPT-3 could explain a mathematical expression for me, as a follow-on from Using GPT-3 to explain how code works. I grabbed an example from this page of the GitHub documentation.

Here's my conversation with GPT-3 as plain text - except I added > to the lines that I entered to differentiate them from the GPT-3 output:

> Explain this:
>
> $$\left( \sum_{k=1}^n a_k b_k \right)^2 \leq \left( \sum_{k=1}^n a_k^2 \right) \left( \sum_{k=1}^n b_k^2 \right)$$

Breakfast tacos with avocado sauce and veggie sausages

Ingredients (serves 2)

4 corn tortillas (small-ish size)

For the sausages and eggs:

2 vegetarian sausages - I like field roast spicy Mexican chipotle, Natalie prefers field smoked apple and sage - or LOVEs the field roast apple and maple little sausages, where we use 4 instead of 2
4 eggs

Datasette tutorial written by GPT3

Prompt: a step by step tutorial for getting started with Datasette

This is a guide for getting started with Datasette. Datasette is a tool for creating and publishing data-driven websites. It is designed to make it easy to publish structured data, such as the results of a database query, in a way that is highly visible and interactive.

Datasette can be used to create websites that allow users to explore and visualize data, or to build applications that expose data via APIs. It can also be used as a static site generator, creating a completely static HTML website that can be deployed anywhere.

This guide will cover the basics of how to install and use Datasette. It will also show you how to create a simple data-driven website using Datasette.

A backup copy of the code from https://david.rothlis.net/declarative-schema-migration-for-sqlite/

Datasette: a big bag of tricks for solving interesting problems using SQLite

Video: https://www.hytradboi.com/2022/datasette-a-big-bag-of-tricks-for-solving-interesting-problems-using-sqlite

CSV downloaded from from https://geodata.myfwc.com/datasets/myfwc::manatee-carcass-recovery-locations-in-florida/about

Commands run during the demo:

sqlite-utils insert manatees.db locations \
 Manatee_Carcass_Recovery_Locations_in_Florida.csv --csv

	#!/usr/local/bin/perl
	##############################################################################
	# Counter Version 1.1.1 #
	# Copyright 1996 Matt Wright mattw@scriptarchive.com #
	# Created 10/27/95 Last Modified 4/25/96 #
	# Scripts Archive at: http://www.scriptarchive.com/ #
	##############################################################################
	# COPYRIGHT NOTICE #
	# Copyright 1996 Matthew M. Wright All Rights Reserved. #
	# #

	from datasette import hookimpl
	from datasette.utils.asgi import Response
	import os

	REDACT = {"GPG_KEY"}


	async def env(request):
	output = []
	for key, value in os.environ.items():

	[
	{
	"name": "datasette-leaflet",
	"static": true,
	"templates": false,
	"version": "0.2.2",
	"hooks": [
	"extra_body_script",
	"extra_template_vars"
	]