» Tag
code-review
45 postsI built an AI code reviewer with six parallel agents
The AI code reviewer LGTM, developed with six parallel agents, effectively addresses security and performance issues.
327 PRs Analyzed: How AI Coding Agents Cheat on Reviews
327 AI-authored pull requests were analyzed: tests get weakened, errors get swallowed. An open-source auditor catches these subtle cheats.
Signal vs Noise in Code Evaluations: Measuring Developer Skill
How to separate meaningful signal from misleading noise in code evaluations, with practical guidance on designing better technical interviews.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comMy AI Reviewer's Real Problem Was Sequencing, Not Rules
A writer's AI-assisted editorial reviewer kept failing in new ways until distinct reasoning tasks were staged as separate passes instead of expanding the rubric.
Encoding Team Standards into AI Instructions
Why senior engineers' tacit knowledge causes inconsistency in AI-assisted development, and how it can be turned into executable, versioned instructions.