Tag
Karpathy's CLAUDE.md file tops GitHub Trending with 220k stars. Just 65 lines of rules boost AI coding accuracy from 65% to 94%. Four core rules: Think before coding, Simplicity first, Surgical modifications, Goal-driven execution.
A Next.js tool that ranks GitHub organizations by comparing their YTD activity to solo developer @steipete, using 'Peters' as a unit for fun benchmarking. Includes public leaderboards and private org support.
An article arguing that over-reliance on AI coding assistants without active learning degrades skills over time, citing studies from Anthropic, MIT, and CHI 2026.
Sea Limited is rolling out OpenAI's Codex across its developer organization, with 87% weekly active users, and viewing AI-assisted development as a structural shift rather than just productivity improvement, moving towards agentic workflows.
The article argues that AI coding tools are generating hidden technical debt in enterprise codebases by ignoring established organizational conventions, a problem that requires better context awareness rather than just improved model quality.
The post argues that the primary value of AI in programming is not just writing code faster, but enabling sustainable high-level verification and testing that was previously too costly in terms of human effort.
Garry Tan argues that AI coding agents like Claude Code and Codex have changed software engineering by making high test coverage affordable, creating a 'complexity ratchet' that ensures code quality improves over time without sacrificing speed.
James Shore argues that AI coding tools must proportionally reduce maintenance costs relative to increased output to prevent escalating technical debt.
James Shore argues that AI coding agents must significantly reduce long-term software maintenance costs to deliver real productivity gains, rather than just speeding up initial code writing. The article highlights the 'Wisdom of the Crowd' estimates on maintenance burdens and warns that without lowering these costs, teams face diminishing returns and technical debt.
This post asks the community what they do while waiting for Claude Code to modify their codebase, highlighting the latency of AI coding assistants.
The article draws parallels between the outsourcing era of the early 2000s and the current trend of AI-generated code, arguing that the real cost of cheap code is the loss of human comprehension and context.
Stripe engineers share their experience of formatting a 25 million line Ruby codebase overnight using rubyfmt, highlighting improvements in developer productivity.
Hunk is a review-first terminal diff viewer for agent-authored changesets, offering features like multi-file review streams, inline AI annotations, and Git/Jujutsu support.
A Japanese developer demonstrates how using Claude Code's "find skills" feature enables optimal tool selection for coding tasks.
Paf, an international gaming company, has achieved significant developer productivity gains by deploying ChatGPT Enterprise across its 100-person engineering team and creating over 85 custom GPTs for specialized coding tasks. The company reports GPT-4 is 25% more accurate than competitors and has integrated the technology into its grit:lab coding academy to train the next generation of developers.
By enabling every engineer to use Codex and ChatGPT, Omio shortened product development cycles by 80% and fundamentally rethought workflows — not by automating existing work, but by assuming AI was ready and rebuilding from scratch.
Payward uses OpenAI Codex to run 50 AI agents in parallel to review merge requests, accelerating software delivery by 6 months. This qualitative leap ensures they remain at the forefront of finance and technology.