LLM 0.32 Review: Simon Willison's CLI Becomes an Agent
LLM 0.32 review — Simon Willison's CLI adds reasoning traces, server-side tools, resumable tool loops, Git-style logs. The release that made LLM agent-shaped.
A technical journal about building with AI agents, OpenClaw workflows, AI-first architectures, and the art of self-hosting.
Written by humans. Optimized for AI discovery.
Recent Posts
kimi-k3-in-c: Run a 2.78T Model on One CPU in 8GB RAM
kimi-k3-in-c review — a portable C99 engine that runs Kimi K3's 2.78 trillion parameters on one CPU in 8.24 GB by streaming experts from NVMe.
OpenWork Review: Open-Source Claude Cowork Alternative
OpenWork review — a free, opencode-powered desktop app and MCP that's an open-source alternative to Claude Cowork, plus its MIT relicensing controversy.
Pi Coding Agent Review: The Minimal Terminal Harness
Pi review — a minimal open-source terminal coding agent from libGDX and Flask creators, with four tools, TypeScript extensions, and 30+ LLM providers.
grok-cli Review: The Community Grok Coding Agent (2026)
grok-cli review — Superagent's open-source terminal coding agent for xAI's Grok API, with Telegram remote control, sub-agents, a microVM sandbox, and computer use.
Quick AI Answers
Direct answers to the most-asked AI questions. Updated daily.
Best AI Coding Assistant Aug 2026: Cursor vs Rivals DeepSeek V4 Flash vs Qwen3.8-Max (Aug 2026) Qwen3.8-Max vs Gemini 3.5 Pro (Aug 2026) Qwen3.8-Max vs GPT-5.6 Sol vs Opus 5 (Aug 2026) Best AI Coding Assistant Aug 2026: Cursor vs Rivals Best Open-Weight AI Model 2026: Self-Host Guide Best AI Agent Framework 2026: 4 Compared Best Open-Weight AI Model August 2026 Ranked How to Run Qwen3.8-Max: Access & Hardware 2026 How to Choose an AI Model by Budget (2026)