Youtop Video Search

It’s always a good day if you see a pelican. In Episode 30 of Talking Postgres with Claire Giordano, open source developer Simon Willison—creator of Datasette and co-creator of Django—joins to explore how AI is useful for data engineers today. We move past the hype and boosterism to dig into example after example: structured data extraction, alt text and accessibility, safety and security (aka the fiddly bits), and why Postgres’s fine-grained permissions are such a good fit for AI-powered workflows. Also: Pulitzer-worthy data tooling, the science fiction of the 10X engineer, agents, MCP, RAG, the multitude of models, and why Simon spends so many waking hours on the jagged frontier of AI. Chapters: ⏩ 00:00 Introducing Simon ⏩ 02:51 Commodore 64 ⏩ 03:49 Origin of Django ⏩ 11:21 Converging LLMs & data journalism ⏩ 12:52 Unreliable sources ⏩ 14:52 Stunningly good at SQL ⏩ 17:45 AI enables ambitious side projects ⏩ 20:33 Science fiction of 10x engineer? ⏩ 21:20 Art of using LLMs & spotting opportunities ⏩ 23:12 Accessibility and Gen AI podcast ⏩ 27:43 Structured data extraction ⏩ 31:20 Video input for Gemini models ⏩ 32:34 Biggest improvement in last 6 months ⏩ 35:29 Safety & security ⏩ 35:58 Postgres is fantastic for this ⏩ 39:50 AI terminology primer ⏩ 53:34 Monthly spend on LLMs ⏩ 54:17 Pelicans on bicycles ⏩ 1:03:55 Honeybadgering with GitHub Codespaces 📜 Full transcript available at: https://talkingpostgres.com/episodes/ai-for-data-engineers-with-simon-willison/transcript ✅ Listen to more episodes of Talking Postgres: https://talkingpostgres.com 💥 Subscribe to Talking Postgres, so you never miss an episode: https://talkingpostgres.com/subscribe Links mentioned in this episode: 🔹 Blog: Simon Willison’s Weblog: https://simonwillison.net/ 🔹 Blog: Simon’s Willison’s TIL - Things I’ve Learned: https://til.simonwillison.net/ 🔹 Podcast episode: Ep01 of Talking Postgres with Simon Willison & Marco Slot: https://youtu.be/Rnz3uJw1DNo?feature=shared 🔹 Django project: https://www.djangoproject.com/ 🔹 Datasette: https://datasette.io/ 🔹 GitHub repo for llm, a CLI tool and Python library: https://github.com/simonw/llm 🔹 Demo of llm CLI tool: https://youtu.be/QUXQNi6jQ30?si=k-t2xq7bQUlg2HK_ 🔹 Blog post: OpenAI’s new open weight (Apache 2) models are really good, by Simon Willison: https://simonwillison.net/2025/Aug/5/gpt-oss/ 🔹 Podcast episode: Accessibility and Gen AI with guest Simon Willison: https://youtu.be/zoxpEM6TLEU?si=8Xf2Yq-zVSx7bcdm 🔹 Blog post: New dashboard: alt text for all my images, by Simon Willison: https://simonwillison.net/2025/Apr/28/dashboard-alt-text/ 🔹 Keynote at Citus Con: An Event for Postgres 2023, by Simon Willison: https://youtu.be/rsE0XhlPnug?si=OoNiZS1_0HPIasIF 🔹 Blog post: How OpenElections Uses LLMs, by Derek Willis: https://thescoop.org/archives/2025/06/09/how-openelections-uses-llms/index.html 🔹 Blog posts tagged with pelican-riding-a-bicycle on Simon Willison’s Weblog: https://simonwillison.net/tags/pelican-riding-a-bicycle/ 🔹 Blog post: “No, AI is not Making Engineers 10x as Productive” via Colton Voege: https://simonwillison.net/2025/Aug/6/not-10x/ 🔹 GitHub repo for the pgvector extension to Postgres: https://github.com/pgvector/pgvector 🔹 Calendar invite: LIVE recording of Ep31 of Talking Postgres to happen on Wed Sep 17, 2025: https://aka.ms/TalkingPostgres-Ep31-cal #TalkingPostgres #podcast #PostgreSQL