Simon Willison demonstrates how ChatGPT Work with GPT‑6 Astra can generate 5K and 10K running routes that loop from a specified address using OpenStreetMap data. The system produced an embedded visualization and downloadable GPX and GeoJSON files, and explained that it used Nominatim, Overpass, and local calculations to create the routes. However, the actual Python code used was not accessible due to thread compaction, highlighting a transparency issue in LLM systems that compact conversation history.
Simon Willison describes a GeoJSON Map Viewer tool he helped build to display local political boundaries for the Granada Community Services District and the Midcoast Community Council. The tool was created through iterations using Claude Code for web and Fable 5.1, and it allows users to export the map as a PNG. The boundaries were sourced from government data via ChatGPT Work, and a link shows both polygons displayed simultaneously on the viewer.
The article describes how the author used Parseable, an observability platform, with Datasette to handle OpenTelemetry traces. Parseable offers an open‑source Rust implementation and an enterprise version, while Datasette 1.0a41 added OpenTelemetry support. The author demonstrates the setup and shows a screenshot of a Datasette trace displayed in Parseable’s local web interface.
Tool: CORS Chat I built this today ( with GPT-5. 6-Sol xhigh ) to help test Qwen 3.
Simon Willison comments on GPT 6.1‑Sol, describing it as "Near‑Astra intelligence for a fifth of the price." He notes that the model’s pelican illustrations are similar to those of the GPT‑6 family and provides links to the live‑blog of the keynote and to the pelican images. The post is tagged with AI, OpenAI, generative‑AI, LLMs, and playful references to pelican‑riding‑a‑bicycle.
Simon Willison created an animated transition tool that morphs a map from the Mercator projection to the Equal Earth projection using D3. The project was inspired by the recent UN vote on the Equal Earth map projection and was built with GPT‑6 Astra (medium) in ChatGPT Work. It showcases how modern AI and web technologies can visualize complex geospatial transformations.
Release: llm-gemini 0. 33 It's been a while since the last llm-gemini release.
Simon Willison tested GPT‑6 Astra by generating SVG pelicans riding bicycles at various reasoning levels and compared the results to GPT‑5.6 Sol, Terra, and Luna. The Astra pelicans consistently outperformed the other models, especially at low and xhigh reasoning levels, and even the Astra max version produced high‑quality images. Astra also used fewer tokens and was roughly twice as expensive as Sol, yet its low‑level output was cheaper and superior to any Sol model.
Simon Willison demonstrates how to use Blender with coding agents on macOS by installing the full Mac application from blender.org and issuing prompts to ChatGPT Codex. He shows a step-by-step example where the agent renders a scene of a pelican riding a bicycle, then adds background flair and improves the image. The resulting image is generated via Blender's Python API.
The article describes a test of the new Python 3.15 profiler using GPT-6 Astra Extra High in Codex to run it against a web-edit application from PyPI. It includes a flame graph and source heatmap generated from this profiling effort. The author emphasizes the use of these visual tools to analyze the performance of the web-edit app.
The article is a comment by Simon Willison on the Mistral Large 4 model, posted on Hacker News. He discusses the saturation of benchmarks and humorously references a benchmark involving an armadillo in fishnet tights jaywalking on Mars, comparing the performance of several large language models including Claude Opus, GPT, Gemini, and Mistral Large 4.
Claude Cowork and the standard chat interface are merging into a single Claude experience, allowing users to hand over tasks or ask quick questions that the system will continue to handle even after the laptop is closed. The rollout will begin with Pro and Max plan users across web, desktop, and mobile, and will extend to new users on these plans over the coming weeks. This integration suggests Claude is evolving into a general agent, simplifying the distinction between Cowork and regular Claude usage.
Stealing Reasoning Traces from Proprietary LLM APIs A vanity domain name ( stolen-thoughts. com ) for a neat paper : Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks to clients that can be replayed across sessions, users, and models.