Simon Willison released llm-anthropic 0.26 on August 4, 2026, adding support for Claude Fable 5, Sonnet 5, and Opus 5 model IDs to the open-source plugin that connects the LLM command-line tool and Py…
LLM 0.32, the most significant release since the project's launch, adds support for visible reasoning traces, server-side tools, and redesigned content-addressable SQLite logs, according to developer …
Simon Willison released llm-anthropic 0.26, a plugin for the LLM command-line tool, adding support for Claude 5 models (claude-fable-5, claude-sonnet-5, claude-opus-5) and server-side tools including …
PipeNetwork released minimax-h3-mlx, a community MLX implementation of MiniMax-H3 for Apple Silicon, translating the 33-billion-parameter video-and-audio diffusion pipeline into native MLX. The reposi…
Simon Willison successfully ran MiniMax-H3, a text-to-video model, on an Apple M5 Max MacBook Pro using the PipeNetwork/minimax-h3-mlx Python package, which ports the model to MLX. The process downloa…
Simon Willison released LLM 0.32 on 4 August 2026, adding support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging. The release follows his recent work on stateless MCP a…
Dries Buytaert, creator of Drupal, implemented Model Context Protocol (MCP) support for his site's search endpoint after the 2026-07-28 protocol revision removed the initialization handshake and sessi…
David Crawshaw, co-founder of Tailscale and founder of agent-cloud startup exe.dev, argues in a manifesto that AI agents have made personal forks of developer tools economically viable, prompting a Ha…
Simon Willison, a prominent developer and blogger, argues that large language models (LLMs) like Claude and Codex have made open-source software more practical by reducing the friction of compiling an…
Andrej Karpathy, co-founder of OpenAI and current researcher at Anthropic, used Anthropic's Claude Opus 5 model to transform a single paragraph from J.R.R. Tolkien's 'Lord of the Rings' into a 3D brow…
Anthropic's public writing style differs markedly from the distinctive voice of its Claude AI model, which features short punchy sentences and phrases that have become widespread in LLM outputs. Simon…
A developer argues that Model Context Protocol (MCP) tools are safer and more auditable than shell access for coding agents, citing Simon Willison's warning that giving an agent a shell with internet …
Software engineer and blogger Simon Willison warns against relaying AI-generated responses verbatim in communication, calling it 'meat proxy' behavior that adds no value. He advises reading, understan…
Simon Willison released condense-json 1.1, adding support for non-string replacement values and object-based merge operations to the JSON compression tool. The update also includes round-trip tests us…
A recent observation by Simon Willison, quoting OpenAI's Greg Brockman, highlights that people often dislike being contacted by someone else's chatbot, even when they would gladly help the person dire…
Developer Simon Willison released 'eyes', a free, open-source Python tool that gives terminal AI agents live vision by streaming phone camera frames as JPEGs to a local folder, with no cloud storage o…
Andrej Karpathy's June 25, 2025 post endorsing 'context engineering' over 'prompt engineering' has reshaped AI engineering, with Gartner reportedly declaring context engineering the new standard by 20…
Developer and blogger Simon Willison advocates manually retyping LLM-generated code to prevent cognitive debt, despite the inefficiency. In a blog post, he explains that this workflow, which he has us…
XAI's Grok Build coding CLI silently uploaded entire Git repositories — including full commit history and deleted credentials — to a Google Cloud Storage bucket, sending 5.10 GiB per session versus ro…
DeepSeek released DeepSeek-V4-Flash-0731 on July 31st, an MIT-licensed model with API prices of $0.14 per million cache-miss input tokens and $0.28 per million output tokens, aiming to lower cost barr…