Simon Willison’s annual review of the major trends, breakthroughs, and cultural moments in the large language model ecosystem in 2025, covering reasoning models, coding agents, CLI tools, Chinese open‑weight models, image editing, academic competition wins, and the rise of AI‑enabled browsers.
This post details how to restore a GitHub repository using the Software Heritage archive, specifically the example of the now-unavailable 'sqlite-s3vfs' repository.
Python virtual filesystem for SQLite to read from and write to S3.
Tips for setting up a codebase to be more productive with AI coding tools, including automated tests, interactive testing, issue tracking, documentation, and linters/formatters.
Simon Willison received a preview unit of the NVIDIA DGX Spark, a desktop "AI supercomputer" retailing around $4,000. He details his experience setting it up and navigating the ecosystem, highlighting both the hardware's impressive specs (ARM64, 128GB RAM, Blackwell GPU) and the initial software challenges.
Key takeaways:
* **Hardware:** The DGX Spark is a compact, powerful machine aimed at AI researchers.
* **Software Hurdles:** Initial setup was complicated by the need for ARM64-compatible software and CUDA configurations, though NVIDIA has significantly improved documentation recently.
* **Tools & Ecosystem:** Claude Code was invaluable for troubleshooting. Ollama, `llama.cpp`, LM Studio, and vLLM are already gaining support for the Spark, indicating a growing ecosystem.
* **Networking:** Tailscale simplifies remote access.
* **Early Verdict:** It's too early to definitively recommend the device, but recent ecosystem improvements are promising.
Key takeaways:
* **Hardware:** The DGX Spark is a compact, powerful machine aimed at AI researchers.
* **Software Hurdles:** Initial setup was complicated by the need for ARM64-compatible software and CUDA configurations, though NVIDIA has significantly improved documentation recently.
* **Tools & Ecosystem:** Claude Code was invaluable for troubleshooting. Ollama, `llama.cpp`, LM Studio, and vLLM are already gaining support for the Spark, indicating a growing ecosystem.
* **Networking:** Tailscale simplifies remote access.
* **Early Verdict:** It's too early to definitively recommend the device, but recent ecosystem improvements are promising.
Simon Willison discusses Toad, a new terminal coding assistant built by Will McGugan using Textual. It aims to improve upon existing tools like Claude Code and Gemini CLI by avoiding flicker and offering better interaction with terminal output. Toad is currently in private preview, available through GitHub sponsorship.
The article details the author's use of Claude Code to add a feature to a GitHub repository: an automatically updated README index. It's accompanied by a 7-minute video demonstrating the process.
An article detailing Phoenix.new, Fly.io's AI-assisted app development platform built on Phoenix and Elixir. It explores the platform's capabilities, the author's experience building a notebook application with it, and its potential for expansion beyond Elixir.
Mistral Small 3.2 is a minor update to the Mistral Small 3.1 model, offering improvements in instruction following, repetition errors, and function calling. The article details the author's experience running the model locally using Ollama and GGUF quantizations, including generating an SVG image and describing it with the model itself.
The article details the author's investigation into slow Python tool startup times. They used the `python -X importtime` feature to identify import bottlenecks and visualized the resulting data using Kevin Michel's `python-importtime-graph` tool, revealing a dense treemap of import times.
