OpenAI releases Codex, a Mac app for agentic coding that uses AI agents to assist with the full software development lifecycle.
Argues against the Agile mantra 'quality is everyone's responsibility' and advocates for dedicated software testing roles.
Explores the unpredictable second-order effects of AI evolution, focusing on how AI coding tools may reshape developer choices and business models.
A developer explains the practical benefits of implementing a --dry-run option in a reporting application for safe testing and validation.
Explains the core concepts of AI coding agents (rules, commands, skills, etc.) and provides a unified mental model for understanding them.
Explores Pi, a minimal coding agent within the OpenClaw project, highlighting its design, tools, and why the author prefers it for agentic programming.
A guide to setting up autonomous AI coding agents that work in continuous loops to write, test, and commit code automatically.
Explores how AI-generated code overwhelms traditional peer review processes, highlighting existing flaws and proposing deeper evaluation methods.
A guide to long-term best practices for managing open-source projects, covering organization, PRs, issues, security, and releases.
Steve Yegge discusses evolving the Beads CLI for AI agents by implementing their 'hallucinations' to create a natural interface.
A theater software CEO shares his journey from AI skepticism to using Claude Code to build a niche lighting app, highlighting AI's role as a programming tool.
A theater software CEO shares his journey from AI skepticism to using Claude Code to build a niche lighting app, discussing AI's impact on programming.
A senior frontend engineer shares their journey of joining Khan Academy, focusing on their role, the job search process, and the challenges of navigating the tech industry.
A software engineer describes replacing a $120/year SaaS tool with a custom LLM-generated solution in just 20 minutes, questioning the future of simple SaaS.
A daily tech reading list covering AI updates from Google, Netflix's Graph Search evolution, multi-agent workflows, and AI's impact on CI and product management.
A critique of the dogmatic adherence to Test-Driven Development (TDD), comparing its 'cult-like' following to trends in software engineering.
Practical strategies for managing large, growing tag systems in web development projects, based on real-world experience.
A five-level model for AI-assisted programming, from basic autocomplete to fully autonomous 'dark factory' software development.
A five-level model for AI-assisted programming, from basic autocomplete to fully autonomous 'dark factory' software development.
A senior engineer reflects on the transition from individual contributor to system designer, exploring the addictive nature of shipping code versus the long-term leverage of building robust systems.
