Experiments with AI coding agents scaling to build a web browser from scratch, generating over a million lines of code.
Experiments with AI coding agents building a web browser from scratch, generating over a million lines of code in a week.
How AI coding assistants are enabling experienced developers to code again by reducing time investment and leveraging management skills.
A Google engineer shares her experience using Claude Code to rapidly prototype a distributed agent orchestrator, highlighting AI's impact on complex software development.
A developer uses AI to create a script for extracting specific file versions from ZFS snapshots, detailing the tool's use case and functionality.
A developer reflects on the anxiety and impact of using Large Language Models (LLMs) in programming, balancing skepticism with practical utility.
A developer revisits building an RSS feed reader using AI coding assistants like Claude Code, detailing the setup, iterative development process, and pricing considerations.
OpenAI releases GPT-5.2-Codex, a model optimized for agentic coding with improvements in refactoring, Windows performance, and cybersecurity.
Anil Madhavapeddy uses AI to port an HTML5 parser and test suite from JavaScript to OCaml, discussing copyright and ethical implications.
An analysis of Claude Code's Plan Mode, explaining its functionality, how it differs from YOLO mode, and its internal implementation.
A developer reflects on the boredom of AI-driven 'vibe coding' and why they still prefer hands-on programming for the joy and learning it provides.
Anthropic acquires Bun, the JavaScript runtime company, to power its Claude Code AI products and accelerate development.
OpenAI releases GPT-5.1-Codex-Max, a new AI model focused on agentic coding tasks, featuring advanced context compaction for long-running work.
Explores how LLMs could lower the barrier to creating and adopting new programming languages by handling syntax and core concepts.
A hands-on review of Cursor 2.0's new Composer AI coding model, testing its speed and code quality with and without structured workflows.
Argues that LLMs serve as a baseline for developer tools, not replacements, due to their general but non-specialized capabilities.
A developer compares Claude Code to OpenCode with different AI models (Sonnet-4, Gemini, GPT-4.1) on a practical coding task, evaluating their performance and workflow fit.
A developer critiques a ZFS snapshot sync script generated by Grok AI, highlighting its flaws and potential dangers.
A developer walks through building a Next.js app using the new Gemini CLI tool, demonstrating its AI-powered coding workflow and troubleshooting.
A developer documents their experience using the gemini-cli tool to create a Chrome Extension with AI assistance, including setup and features.
