S04E02 - Programming with AI - with Simon Willison

S04E02 - Programming with AI - with Simon Willison

Author: Half Stack Data Science March 31, 2025 Duration: 50:01

In this episode we talked to Simon Willison.

Simon is the creator of Datasette, an open source tool for exploring and publishing data. He currently works full-time building open source tools for data journalism, built around Datasette and SQLite.

Prior to becoming an independent open source developer, Simon was an engineering director at Eventbrite. Simon joined Eventbrite through their acquisition of Lanyrd, a Y Combinator funded company he co-founded in 2010.

He is a co-creator of the Django Web Framework, and has been blogging about web development and programming since 2002 at simonwillison.net

We talked to Simon about his goal of building tools for data journalists, what he's learned about tinkering with, and writing about, AI models for years, his excitement about their code-generating capabilities, how to get the most out of all of these tools, and what generative AI tools have to do with pelicans.

You can find Simon at https://simonwillison.net

Please enjoy our conversation with Simon Willison!

--

David's book, The Well-Grounded Data Analyst is out! ⁠https://www.manning.com/books/the-well-grounded-data-analyst⁠

If you want to find out more, we have a whole episode about it: ⁠https://open.spotify.com/episode/5D0iDtQRh3tWiIhokrjz3x?si=AiX6YyRET16lnzXDlvdcfw


Hosted by David Asboth and Shaun McGirr, Half Stack Data Science pulls back the curtain on what it really means to build and deploy data science within large organizations. This isn't a theoretical discussion of algorithms, but a grounded conversation about the messy, human, and often political challenges that define the field in an enterprise setting. Each episode delves into the practical hurdles-from managing stakeholder expectations and navigating legacy systems to communicating value and dealing with imperfect data. You'll hear candid reflections on projects that succeeded and those that didn't, offering a rare, unvarnished look at the day-to-day work beyond the hype. The Half Stack Data Science podcast is for practitioners who want to move beyond textbook examples and for leaders seeking to understand how to foster effective data teams. It’s a dialogue focused on the tools, processes, and soft skills necessary to deliver impact, making it an essential listen for anyone navigating the complex intersection of data, technology, and business reality. Tune in for honest talk about building things that actually work.
Author: Language: English Episodes: 33

Half Stack Data Science
Podcast Episodes
S03E08 - The market view of data education - with Richie Cotton [not-audio_url] [/not-audio_url]

Duration: 46:30
A reminder that David's book, Solve Any Data Analysis Problem, is out later this year and you can already buy it and read it in its draft form as part of Manning's Early Access Program. If you want to practise your data…
S03E07 - The power of data storytelling - with Kat Greenbrook [not-audio_url] [/not-audio_url]

Duration: 47:40
A reminder that David's book Solve Any Data Analysis Problem is available in Manning's Early Access Program! You can read more about it here: ⁠https://www.manning.com/books/solve-any-data-analysis-problem⁠ (if it's not o…
S03E06 - Reimagining data analytics training - with James Cotton [not-audio_url] [/not-audio_url]

Duration: 54:47
First of all, David's book Solve Any Data Analysis Problem is available in Manning's Early Access Program! You can read more about it here: https://www.manning.com/books/solve-any-data-analysis-problem (if it's not on of…
S03E05 - Code quality for data science - with Laszlo Sragner [not-audio_url] [/not-audio_url]

Duration: 45:11
In this episode, we continued our season of talking to data educators and spoke to Laszlo Sragner. Laszlo runs Hypergolic, a boutique consultancy in London specialising in Machine Learning Product Management. Formerly, h…
S03E04 - The language of data literacy - with Valerie Logan [not-audio_url] [/not-audio_url]

Duration: 50:04
Continuing our series of conversations with data educators, in this episode we spoke to Valerie Logan. Founding The Data Lodge in 2019, Valerie is as committed to data literacy as it gets. She believes that in today's di…
S03E03 - Effective Python teaching - with Matt Harrison [not-audio_url] [/not-audio_url]

Duration: 36:30
In this episode of Half Stack Data Science we continue our season 3 all about data science education, with a conversation with Matt Harrison. Matt stands as a prominent figure in the Python and data science community. A…
S03E02 - The joy of teaching Python - with Reuven Lerner [not-audio_url] [/not-audio_url]

Duration: 40:47
In this episode of Half Stack Data Science we continue our season 3, all about data science education, with a conversation with Reuven Lerner. Reuven is a full-time Python trainer with a bachelor's degree in computer sci…
S03E01 - Preparing analysts for the real world - with Lisa Carpenter [not-audio_url] [/not-audio_url]

Duration: 36:24
In this episode, David & Shaun talk to Lisa Carpenter. Lisa is the lead data science instructor at Digital Futures, with responsibility for the design and delivery of the Data Science programme. Prior to transitioning to…
Season 3 Teaser [not-audio_url] [/not-audio_url]

Duration: 4:20
The Half Stack Data Science podcast is back (again)! Season 3 is coming very soon. In the meantime, listen to our teaser episode where we briefly recap our first 2 seasons and introduce the concept behind season 3; a ser…