LLM 0.32 adds reasoning traces, OpenAI Responses, server-side tools, and smarter logging for CLI and Python API.
Release notes for llm-anthropic 0.26, adding new Claude models, server-side tools, and streaming improvements.
Simon Willison announces LLM 0.32, a command-line tool for accessing large language models, with new features like reasoning traces and OpenAI Responses support.
Explores why hobby programming communities are hostile to LLM usage, emphasizing craft, learning, and earned respect over generated code.
Simon Willison discusses Niklas Gruhn's term 'meat proxy' for people who blindly copy AI output, urging readers to understand and validate AI responses before relaying them.
A comment on Hacker News discussing how LLMs make open source software more accessible for modification, reducing friction in building and understanding code.
A practical guide to building an LLM-operated Markdown knowledge graph for a second brain, focusing on structure, workflows, and maintenance.
Comparison of LangChain, LangGraph, and Microsoft Agent Framework for building AI applications, focusing on ecosystem fit, architecture, and use cases.
Explore building a second brain with LLMs and AI agents, focusing on durable context systems for knowledge work.
DeepSeek-V4-Flash-0731 is a new 304B parameter AI model with enhanced agentic capabilities, offering high performance at low cost.
Simon Willison announces llm-mcp-client 0.1a0, a tool that lets LLMs access tools from MCP servers.
Release notes for llm 0.32rc2, a CLI tool for accessing LLMs, featuring new default model GPT-5.6 Luna and an 'openai endpoint' command.
Release of llm-chat-completions-server 0.1a0, an LLM plugin that serves an OpenAI Chat Completions API endpoint, enabling conversation tracking with content-addressable logs.
LLM 0.32rc1 release adds content-addressable hash IDs for messages, de-duplication, and support for new GPT-5.6 models.
Anthropic researchers used Claude Mythos to find cryptographic weaknesses in HAWK and AES, sharing prompts and insights.
Explains why externalizing judgment is the key skill for using LLMs effectively, beyond prompt engineering.
Explores how LLMs impact software engineering standards, warning against vibe-coding and loss of code ownership.
Explores whether code quality remains important when LLMs generate code, questioning if human-centric quality standards apply in an AI-driven future.
Analysis of AI tools in Linux kernel development, including Linus Torvalds' stance on AI for code authoring and review.
A curated reading list covering AI models, reliability, LLM code familiarity, tokenomics, and tech career shifts.
