726 related articles
Product ReviewsHands-on test of OpenAI Codex CLI with a visual novel game task, compared against Claude Code and Gemini CLI on planning, code quality, and completion.
Deep DivesHow Playground Skill uses HTML interactive interfaces to solve the pain points of natural language limitations in AI coding. Comparing traditional text-only modes with the new two-way interaction paradigm for Coding Agents.
TutorialsStep-by-step OpenManus local deployment guide covering Conda setup, DeepSeek API configuration, and 3 real-world test cases validating AI Agent capabilities including web search and file generation.
TutorialsDeep dive into Grammar-Constrained Decoding (GCD) technology: applying Bash syntax constraints during inference to dramatically improve small language models' code generation correctness and executability for AI Agent edge deployment.
TutorialsDjango co-creator Simon Willison used Claude Code on his phone to build an iNaturalist wildlife sighting sync feature for his blog, showcasing AI-assisted mobile development.
Tech Frontiersdatasette-llm 0.1a7 adds model default configuration, supporting preset temperature and other parameters for specific LLMs to standardize batch data enrichment.
TutorialsSimon Willison built a complete iNaturalist observation aggregation tool using only his phone and Claude Code while camping. A detailed look at the Python CLI, Git Scraping, and static frontend architecture.
Tech FrontiersOpenAI Codex CLI 0.128.0 introduces the /goal command, enabling autonomous looping until objectives are met or token budgets are exhausted. Analysis of its Ralph Loop implementation and safety controls.
Tech FrontiersSimon Willison releases llm-echo 0.5a0 with a new thinking option to simulate LLM chain-of-thought output. Learn how this testing plugin streamlines AI development workflow automation.
Product ReviewsDeep dive into AnythingLLM, a privacy-first, zero-config local AI productivity platform. Supports RAG document chat, multi-model integration, knowledge bases, and AI Agents with nearly 60K GitHub stars.
Product ReviewsDeep dive into Chatbox, an open-source AI client with nearly 40K GitHub Stars. Supports GPT-4, Claude, Gemini multi-model switching, local data storage for privacy, and cross-platform desktop use.
Deep DivesSimon Willison releases LLM 0.32a0 alpha with a major refactor introducing message sequence API, typed streaming output, and flexible serialization while maintaining backward compatibility.
TutorialsA detailed guide to Simon Willison's open-source tool inaturalist-clumper 0.1, which automatically clusters iNaturalist observation records by time and location, outputting JSON for nature blogs, data visualization, and static site integration.
TutorialsComplete guide to Open Agent Builder: an open-source visual AI agent builder with local deployment steps, stock analysis demo, and comparison with n8n and OpenAI Agent Builder.
TutorialsOpenAI open-sources GPT-OSS (20B/120B) with MOE architecture and native FP4 precision. Run O3-level reasoning on a single RTX 4090. Full deployment guide for Ollama, vLLM, and more.
Product ReviewsDeep dive into Get Shit Done (GSD), a 62K-star GitHub project built for Claude Code. Covers meta-prompting, context engineering & spec-driven development.
Tech FrontiersGitHub project andrej-karpathy-skills earned 130K Stars with a single CLAUDE.md file, converting Karpathy's LLM coding pitfall insights into AI behavioral guidelines for Claude Code.
Product ReviewsComprehensive review of FreeBuff Coder free terminal AI coding assistant, covering its 9 sub-agents, DeepSeek V4 model routing, IPIR workflow, privacy concerns, and comparison with Claude Code.
Tech FrontiersSimon Willison built a QR code generator with Claude AI, supporting URL text and WiFi QR code generation with style customization. A detailed look at this vibe-coding project's design and AI-assisted development insights.
TutorialsComplete guide to using Zhipu GLM-4.5 for free: web-based full-stack development, one-sentence PPT generation, and API integration with Claude Code for cost-effective programming workflows.