Simon Willison introduces GPT‑6 Astra, a new model that offers improved attention to detail, better prompt comprehension, and the ability to generate more sophisticated outputs. The model excels at creating 3D renderings, producing detailed scenes such as gardens, shipyards, animals, cityscapes, and even Dyson spheres. Willison highlights its whimsical creativity, noting examples like a pelican wearing a red neckerchief riding a bicycle.
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.
The article announces the release of llm version 0.35, which introduces a new OpenAI model named gpt-6-astra for GPT-6 Astra. It highlights the addition of this model to the llm library and tags the release with openai, llm, and gpt-6-astra.
Simon Willison created a video compressor tool that uses the WebAssembly build of FFMPEG to optimize a demo video of his Equal Earth animation recorded on his phone. He employed Claude Fable 5.1 in Claude Code for web to generate the tool, enabling him to publish the optimized video on his blog. The project showcases how modern web technologies can streamline video processing workflows.
The release of llm-gemini 0.34 introduces the new Gemini 3.8‑Flash model, available in low, medium, and high thinking levels, and fixes an issue where async responses failed to record the resolved model version. The update also notes that Google has released Gemini 3.8‑Flash (and a restricted 3.8 Flash Cyber version) today, with example outputs (pelicans) demonstrating the model’s performance across the different thinking levels. The author highlights Gemini Flash’s speed, low cost, and competence in generating HTML, JavaScript, and Markdown‑SVG content, citing a 13‑second, 1.8‑cent example of an HTML output.
Qwen 3. 8 27B scores 52 on the Artificial Analysis Intelligence Index That's the same score as GPT-5.
I started building my markdown-svg-renderer tool in May , but I've since added enough features to it that it's worth talking about here again. It's evolved into my ideal tool for sharing Markdown transcripts that include SVG documents.
After I released version 1. 0, I figured I would have to do the rotations myself.
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 announces that Claude Code will now support AGENTS.md files starting with version 2.1.277. If a CLAUDE.md file is absent in a folder, Claude will automatically look for and use AGENTS.md, leveraging Claude Code mods to customize the harness. The built‑in mod is available for use, and users can also create their own custom project instructions.
Simon Willison created a .blend URL Viewer tool that lets users view a Blender model of a Fabergé egg themed after the TV show Pluribus directly in their browser. He generated the egg image using ChatGPT Images 2.5, then fed it to GPT‑6 Astra with a custom Blender skill to produce several .blend files. The viewer, built with JavaScript, is now part of his tools collection for easy access to the resulting 3D model.
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.