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.
This article discusses a new paper outlining design patterns for mitigating prompt injection attacks in LLM agents. It details six patterns – Action-Selector, Plan-Then-Execute, LLM Map-Reduce, Dual LLM, Code-Then-Execute, and Context-Minimization – and emphasizes the need for trade-offs between agent utility and security by limiting the ability of agents to perform arbitrary tasks.
LLM 0.26 introduces tool support, allowing LLMs to access and utilize Python functions as tools. The article details how to install, configure, and use these tools with various LLMs like OpenAI, Anthropic, Gemini, and Ollama models, including examples with plugins and ad-hoc functions. It also discusses the implications for building 'agents' and future development plans.
A summary of a workshop presented at PyCon US on building software with LLMs, covering setup, prompting, building tools (text-to-SQL, structured data extraction, semantic search/RAG), tool usage, and security considerations like prompt injection. It also discusses the current LLM landscape, including models from OpenAI, Gemini, Anthropic, and open-weight alternatives.
This article details a new plugin, llm-video-frames, that allows users to feed video files into long context vision LLMs (like GPT-4.1) by converting them into a sequence of JPEG frames. It showcases how to install and use the plugin, provides examples with the Cleo video, and discusses the cost and technical details of the process. It also covers the development of the plugin using an LLM and highlights other features in LLM 0.25.
An analysis of the recent paper 'The Leaderboard Illusion' which critiques the Chatbot Arena's LLM evaluation methodology, focusing on issues with private testing, unfair sampling, and potential gaming of the leaderboard. It also explores OpenRouter as a potential alternative ranking system.
