CODE QUALITY

OwlPath encodes code into an OWL2 ontology so coding agents can answer multi-hop structural queries with SPARQL, cutting tokens 28.8% on SWE-bench Pro.

SWE-NFI benchmarks coding agents on 188 behavior-preserving improvement tasks. The best hits 70% correctness, but all lag humans on structural refactors.

Opus 5 on SlopCodeBench hit a 24% strict pass rate, beating Opus 4.8 and Sonnet 5, yet code quality still degraded. What it shows about coding agents over time.

Write code like a human will maintain it: why AI-generated shortcuts teach future models bad patterns, and what the HN debate suggests for keeping quality up.

A controlled study of 660 Claude Code trials shows clean codebases reduce token usage by 7-8% and file revisitations by 34%, while pass rates stay the same. Traditional maintainability principles still matter in the age of AI coding.

Does code cleanliness affect AI coding agents? A SonarSource study finds the same pass rate, but 7-8% fewer tokens and 34% fewer file revisits on clean code.

FrontierCode grades AI coding agents on whether maintainers would merge their PRs, not on passing tests. Why SWE-Bench misleads and how to adjust review.