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.
An analysis of the current LLM landscape in 2026, focusing on the shift from 'vibe coding' to more efficient and controlled workflows for software development and data analysis. The author advocates for tools like AI Studio and OpenCode, and discusses the strengths of models like Gemini 2.5 Pro and Claude Sonnet.
An extensible Model Context Protocol (MCP) server that provides intelligent semantic code search for AI assistants. Built with local AI models using Matryoshka Representation Learning (MRL) for flexible embedding dimensions.
A review of the SearchResearch blog's 2025 posts, highlighting a shift towards AI-augmented research methods, testing AI tools, and emphasizing the importance of verification and critical thinking in online research.
This article provides a verified list of AI crawlers (GPTBot, ClaudeBot, Gemini, etc.) with user-agent strings, crawl rates, and IP verification information to help manage access and maintain inclusion in AI discovery.
Fine-tune DeepSeek models using your own markdown files as training data. Converts your notes/docs into high-quality Q&A pairs using Gemini, then trains a personalized LLM via Tinker cloud GPUs.
A $50 Raspberry Pi and Whisplay HAT combination offers a customizable, open-source AI chat device that can utilize Gemini, Claude, or ChatGPT, providing an alternative to closed-ecosystem AI gadgets.
This guide covers how you can leverage AI tools to build AI-powered features for your Flutter apps and streamline your Flutter and Dart development.
The author discusses how integrating Google Keep with Gemini has revitalized their use of the note-taking app, allowing for more powerful organization and information retrieval.
This article details a method for finding books on your shelves using Gemini's text recognition capabilities. The author describes how taking pictures of bookshelves and using AI to scan them can help locate lost books and even provide insights into reading habits.
