» Tag
code-review
42 postsCodeClone 2.1: why your AI agent's diff isn't enough
CodeClone 2.1.0a1 introduces a structural change-control layer that bounds AI agent edits in Python codebases before they happen, not just reviews the diff after.
AI Code Audit: 15 Security Flaws Claude Found in Production
An LLM-based security audit uncovered 15 OWASP-classified flaws-SQL/NoSQL injection, IDOR, path traversal-each shown with vulnerable and fixed code.
AI-Generated PRs Can Conceal Malicious Intent Across Multiple Changes
AI-assisted development introduces new challenges in code review. Malicious intent can be hidden across multiple pull requests.
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.comWhy Your AI Code Assistant Needs a Static Pre-Pass
BrassCoders feeds deterministic static-analysis output to LLMs, boosting both speed and accuracy in code review, backed by 2025 research on the pairing.
revert_guard.py Stops AI Agents From Re-adding Reverted Code
revert_guard.py reads a repo's own git revert history to block AI agents from re-adding previously reverted code, like a card_token column, before it gets committed—offline and keyless.
Quality is the New Quantity
AI has made software development cheaper, but quality is now the bottleneck. Teams need shared understanding.
GitHub's Copilot Code Review: Lessons from Tool Migration
GitHub's Copilot code review faced challenges with shared tools. Clearer instructions led to a 20% reduction in review costs.
I 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.