Talking Postgres with Claire Giordano AI for data engineers with Simon Willison
Aug 8, 2025
Simon Willison, an open source developer and creator of Datasette, dives into how AI is reshaping data engineering. He shares the importance of structured data extraction and accessibility, underscoring Postgres's fit for AI projects. Their discussion spans the transformative power of AI in journalism, the evolving role of tools like large language models in data tasks, and the humorous benchmark of pelicans in AI-generated art. Willison also highlights essential AI tools, pushing for a playful and adaptive use of technology.
AI Snips
Chapters
Transcript
Episode notes
From Commodore 64 To Django
- Simon learned programming on a Commodore 64 and later co-created Django while interning at a Kansas newspaper.
- That newspaper work led to open-sourcing Django and a long career in data journalism tools.
LLMs Expand Who Can Query Data
- LLMs let non-programmers ask complex data questions by providing model-backed tools that translate intent into queries.
- This makes advanced data exploration feasible for journalists without SQL or Python skills.
Show Work And Enable Peer Review
- Don't just give users a final answer; show the model's working steps and query structure so they can verify results.
- Provide shareable URLs and peer review hooks so others can audit model-generated queries before publishing.