code-quality

The article introduces a CLI tool called 'malveon check' that verifies code completion by running build, lint, and test commands to prevent AI agents from falsely declaring tasks done.

GitHub Podcast discusses AI hot takes, questioning if fine-tuning models for codebases indicates bad code and inviting listener opinions.

A developer recounts spending hours using tools like fable, sol, and grok for code review and simplicity checks, only to produce what they describe as one of the worst interfaces.

ImpactGate is a tool that measures and gates the structural decay introduced by code changes, using a scoring formula to encourage refactoring and maintain code quality.

Ryan Peterman interviews Casey Muratori about computer history, software engineering, and programming practices in a podcast episode focused on balanced tech discussion.

The article highlights how coding agents introduce technical debt in software systems and proposes using tools like ArchUnitPython to enforce architectural rules and prevent structural issues.

Boris Cherny emphasizes the need for higher standards and guardrails when using AI models like Claude for production code to maintain quality and avoid maintenance issues.

The article explores how LLMs can generate correct code but often introduce sloppiness like unnecessary abstractions, and discusses methods to measure code quality, including using AI judges and human evaluation.

This article emphasizes the need for trust in AI-generated code within engineering teams and outlines practices such as accountability, coding guidelines, and deterministic tooling to uphold code quality.

The article critiques the AI model GPT 6 Astra for generating poor-quality code in software engineering tasks despite its impressive capabilities, suggesting that AI training may reward task completion over output quality.

Simon Willison argues that completely rewriting legacy systems from scratch rarely succeeds and typically results in two parallel systems in production. He recommends shoring up the old system with automated testing and targeted refactors instead, citing Will Larson's writing on migrations as the best responsible approach.

Zach Kehs observes that unlike physical buildings, software faces no structural ceiling and can always degrade further through additional layers of indirection and reduced performance.

The article explores whether AI tools are accelerating learning for junior developers or merely enabling task completion without deep understanding, based on insights from experienced engineers.

This article is the first part of a guide to pstack, a personal set of engineering skills and tools that includes verification skills and aids in building high-quality AI applications like Grok Bot.

Sandy Metz discusses making code small and using tests to guide refactoring, illustrated through the Gilded Rose kata.

The article explains that AI review loops in code development can become unstable due to inconsistent AI opinions, scope creep, and hallucinations, as shown in a test with Opus 5.

GitHub has released 4 new Skills exercises designed to give developers practice with AI-powered development, agentic workflows, and code quality.

The author tested GenOS, a tool for LLM agents using versioned YAML genomes, and found it outperformed traditional prompting and multi-agent swarms by reducing token overhead and enhancing code quality through emergent TDD and agent breeding.

The article shares a method using an agent.md file to define coding style preferences for LLM-assisted development, improving code quality by reducing repetitive feedback.

Robert C. Martin discusses his career, the impact of 'Clean Code', and his approach to using AI agents with constraint tools like static analysis and mutation testing to enhance software development.