Entries
Filters: Sorted by date
What AI can do for you on the Theory of Change podcast
Matthew Sheffield invited me on his show Theory of Change to talk about how AI models like ChatGPT, Bing and Bard work and practical applications of things you can do with them.
[... 548 words]AI-enhanced development makes me more ambitious with my projects
The thing I’m most excited about in our weird new AI-enhanced reality is the way it allows me to be more ambitious with my projects.
[... 3,336 words]I built a ChatGPT plugin to answer questions about data hosted in Datasette
Yesterday OpenAI announced support for ChatGPT plugins. It’s now possible to teach ChatGPT how to make calls out to external APIs and use the responses to help generate further answers in the current conversation.
[... 1,801 words]Weeknotes: AI won’t slow down, a new newsletter and a huge Datasette refactor
I’m a few weeks behind on my weeknotes, but it’s not through lack of attention to my blog. AI just keeps getting weirder and more interesting.
[... 1,255 words]Don’t trust AI to talk accurately about itself: Bard wasn’t trained on Gmail
Earlier this month I wrote about how ChatGPT can’t access the internet, even though it really looks like it can. Consider this part two in the series. Here’s another common and non-intuitive mistake people make when interacting with large language model AI systems: asking them questions about themselves.
[... 1,950 words]A conversation about prompt engineering with CBC Day 6
I’m on Canadian radio this morning! I was interviewed by Peter Armstrong for CBC Day 6 about the developing field of prompt engineering.
[... 1,742 words]Could you train a ChatGPT-beating model for $85,000 and run it in a browser?
I think it’s now possible to train a large language model with similar functionality to GPT-3 for $85,000. And I think we might soon be able to run the resulting model entirely in the browser, and give it capabilities that leapfrog it ahead of ChatGPT.
[... 1,751 words]Stanford Alpaca, and the acceleration of on-device large language model development
On Saturday 11th March I wrote about how Large language models are having their Stable Diffusion moment. Today is Monday. Let’s look at what’s happened in the past three days.
[... 2,055 words]Large language models are having their Stable Diffusion moment
The open release of the Stable Diffusion image generation model back in August 2022 was a key moment. I wrote how Stable Diffusion is a really big deal at the time.
[... 1,815 words]ChatGPT couldn’t access the internet, even though it really looked like it could
A really common misconception about ChatGPT is that it can access URLs. I’ve seen many different examples of people pasting in a URL and asking for a summary, or asking it to make use of the content on that page in some way.
[... 1,745 words]Weeknotes: NICAR, and an appearance on KQED Forum
I spent most of this week at NICAR 2023, the data journalism conference hosted this year in Nashville, Tennessee.
[... 1,941 words]Thoughts and impressions of AI-assisted search from Bing
It’s been a wild couple of weeks.
[... 1,763 words]In defense of prompt engineering
Prompt engineering as a discipline doesn’t get nearly the respect it deserves.
[... 924 words]I talked about Bing and tried to explain language models on live TV!
Yesterday evening I was interviewed by Natasha Zouves on NewsNation, on live TV (over Zoom).
[... 1,697 words]Analytics: Hacker News v.s. a tweet from Elon Musk
My post Bing: “I will not harm you unless you harm me first” really took off.
[... 817 words]Bing: “I will not harm you unless you harm me first”
Last week, Microsoft announced the new AI-powered Bing: a search interface that incorporates a language model powered chatbot that can run searches for you and summarize the results, plus do all of the other fun things that engines like GPT-3 and ChatGPT have been demonstrating over the past few months: the ability to generate poetry, and jokes, and do creative writing, and so much more.
[... 4,922 words]Weeknotes: A bunch of things I learned this week, plus datasette-explain
The Datasette table view refactor, JSON redesign and ?_extra= continues this week, mainly in this ongoing pull request and this tracking issue.
datasette-scraper, Big Local News and other weeknotes
In addition to exploring the new MusicCaps training and evaluation data I’ve been working on the big Datasette JSON refactor, and getting excited about a Datasette project that I didn’t work on at all.
[... 1,744 words]Exploring MusicCaps, the evaluation data released to accompany Google’s MusicLM text-to-music model
Google Research just released MusicLM: Generating Music From Text. It’s a new generative AI model that takes a descriptive prompt and produces a “high-fidelity” music track. Here’s the paper (and a more readable version using arXiv Vanity).
[... 1,323 words]Weeknotes: AI hacking and a SpatiaLite tutorial
Short weeknotes this time because the key things I worked on have already been covered here:
How to implement Q&A against your documentation with GPT3, embeddings and Datasette
If you’ve spent any time with GPT-3 or ChatGPT, you’ve likely thought about how useful it would be if you could point them at a specific, current collection of text or documentation and have it use that as part of its input for answering questions.
[... 3,447 words]Datasette 0.64, with a warning about SpatiaLite
I release Datasette 0.64 this morning. This release is mainly a response to the realization that it’s not safe to run Datasette with the SpatiaLite extension loaded if that Datasette instance is configured to enable arbitrary SQL queries from untrusted users.
[... 675 words]2022 in projects and blogging
In lieu of my regular weeknotes (I took two weeks off for the holidays) here’s a look back at 2022, mainly in terms of projects and things I’ve written about.
Weeknotes: Datasette 0.63.3, datasette-ripgrep
We’re back in the UK to see family over Christmas (our first trip back since 2019). Here are a few notes from the past couple of weeks.
[... 801 words]Datasette 1.0a2: Upserts and finely grained permissions
I’ve released the third alpha of Datasette 1.0. The 1.0a2 release introduces upsert support to the new JSON API and makes some major improvements to the Datasette permissions system.
[... 2,844 words]Over-engineering Secret Santa with Python cryptography and Datasette
We’re doing a family Secret Santa this year, and we needed a way to randomly assign people to each other without anyone knowing who was assigned to who.
[... 2,044 words]Weeknotes: datasette-ephemeral-tables, datasette-export
Most of what I’ve been working on for the past week and a half is already documented:
[... 603 words]AI assisted learning: Learning Rust with ChatGPT, Copilot and Advent of Code
I’m using this year’s Advent of Code to learn Rust—with the assistance of GitHub Copilot and OpenAI’s new ChatGPT.
[... 2,661 words]A new AI game: Give me ideas for crimes to do
Less than a week ago OpenAI unleashed ChatGPT on the world, and it kicked off what feels like a seismic shift in many people’s understand of the capabilities of large language models.
[... 1,069 words]Datasette’s new JSON write API: The first alpha of Datasette 1.0
This week I published the first alpha release of Datasette 1.0, with a significant new feature: Datasette core now includes a JSON API for creating and dropping tables and inserting, updating and deleting data.
[... 2,817 words]