Alibaba’s Qwen team released the Qwen 3 model family, offering a range of sizes and capabilities. The article discusses the model's features, performance, and the well-coordinated release across the LLM ecosystem, highlighting the trend of better models running on the same hardware.
Google's Gemini 2.5 Flash model is a new, faster, and more cost-effective model with adjustable 'thinking' capabilities. The article details how to use it with llm-gemini, explores pricing differences compared to Gemini 2.0 Flash, and shares example SVG outputs.
LLM 0.24 introduces fragments and template plugins to better utilize long context models, improving storage efficiency and enabling new features like querying logs by fragment and leveraging documentation. It also details improvements to template handling and model support.
A review of the Qwen2.5-VL-32B large language model, noting its performance, capabilities, and how it runs on a 64GB Mac. Includes a demonstration with a map image and performance statistics.
Simon Willison discusses his experience using Large Language Models (LLMs) for coding, providing detailed advice on how to effectively use LLMs to augment coding abilities, set reasonable expectations, manage context, and more.
A guide on using large language models (LLMs) for programming tasks, including examples, strategies, and useful tips for effectively using AI assistants like ChatGPT and Claude.
Simon Willison discusses the release of llm-anthropic 0.14, which adds support for Claude 3.7 Sonnet's new features. Key features include extended thinking mode, a massive increase in output limits, and improved support for long tasks. The article also covers the plugin's implementation details and limitations.
New release of shot-scraper CLI tool for taking screenshots and scraping web pages with support for HTTP Archive (HAR) files.
This article discusses the utility and implementation of URL-addressable Python environments using Pyodide and WebAssembly, exemplified through Datasette Lite, a browser-based version of Datasette, a Python web application.
OpenAI's documentation for their o1 and o3 'reasoning models' includes tips on how to best prompt them, such as using developer messages, delimiters, and specific instructions.
