AST-Grep
AssessTools
A structural code-search and rewriting tool used to flag code patterns.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by research-stage coverage, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 5Hacker News·9/11/2026researchMeasuring Code Sloppiness in LLM-Generated Software
The article argues that while LLMs can generate code that passes tests, they still often introduce unnecessary abstractions, duplication, and other forms of software slop. It reviews several ways to measure code quality, including AI judges, human review, simple LOC changes, and metrics such as verbosity from the SlopCodeBench paper.