A developer's month-long experiment with OpenAI's Codex, exploring how AI is fundamentally changing software development and the programmer's role.
Argues that AI coding agents should be used to improve code quality and reduce technical debt, not just speed up development.
Explores how modern LLM coding agents adapt to new or private tools, challenging the 'Choose Boring Technology' assumption.
A developer shares a real conversation with Claude Code, an AI coding assistant, to fix bugs in a Delphi IDE expert plugin.
Martin Fowler shares insights from a software retreat on how LLMs impact senior, mid-level, and junior developers, and discusses cognitive debt.
David Crawshaw reflects on the joy and exploration AI agents bring to programming, while acknowledging broader societal fears about AI.
An OpenAI researcher describes using Codex AI to automate due diligence, code exploration, and hyperparameter tuning for experiments.
An OpenAI researcher describes using Codex AI to automate code exploration, experiment setup, and hyperparameter tuning for unfamiliar codebases.
A developer explores using AI coding agents like Claude to automate software development, research, and experimentation, focusing on implementing AlphaGo from scratch.
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.
Explores the Ralph Wiggum Loop, an autonomous agent pattern for software development, with a practical example using IBM Bob.
How Claude Code AI was used to build an automated pipeline for publishing a poetry book, from manuscript parsing to PDF and website generation.
A developer uses Claude Code AI to migrate a static talks website from a paid platform to a self-built Hugo site, exploring AI-assisted web development.
An analysis of using AI to generate automated tests, arguing it misses the point of TDD and reduces testing to a superficial ceremony.
Explains Recursive Language Models (RLMs), which are LLMs that call themselves to break complex tasks into structured, reusable steps.
Explores the challenges of using AI coding assistants, comparing them to the movie '50 First Dates' and emphasizing the need for persistent documentation.
A developer's personal journey through a difficult year leads to insights on how AI is transforming software development and enabling the rise of the micro-entrepreneur.
The core challenge of programming is translating ambiguous human thought into precise computational logic, not just writing code.
