Simon Willison is a software engineer and writer who publishes practical notes on technology and AI. Recently he used GPT‑6 Astra with Nominatim and Overpass to generate running routes and export GPX/GeoJSON, raising issues about hidden code in the UI; he has also commented on production-code standards for Claude and on data-use questions around OpenAI and the Navier–Stokes Millennium Prize.
Pelican-Bicycle Benchmark: 2026 UpdateInspired by Simon Willison, the author reran an SVG-generation benchmark in 2026 using stronger models: 10 of 30 prompts were run through six models on OpenRouter, costing about $20 before stopping.
Generating running routes with GPT‑6 AstraThe author asked ChatGPT Work (GPT‑6 Astra) to generate 5K/10K loop routes from their address. The assistant used Nominatim and Overpass to fetch OSM data and produced visualizations plus GPX/GeoJSON files, but the exact code and steps were hidden in the UI and lost after thread compaction; the author argues systems must preserve pre‑compacted text and make it accessible via agent/tool calls for transparency.
"Production code written by Claude should have a higher bar than if it was written by a human" 💯 [Quoting @bcherny]: Hey ████, I think there is room for both. 1. Prototypes and other throw-away code can be treated as totally black box. If you’re going to thr…
Wrote up my thoughts on the whole OpenAI Navier–Stokes Millennium Prize Problem story, and how it highlights the still confusing question of what using my data "to improve model performance" actually means https://t.co/vgheVu3rw3 https://t.co/dXoCrQPqDm
The A.I. Daily