Skip to main content
Newv0.15.0: fairer scoring.Read the changelog →

Guides and deep dives.

How-to guides, pattern breakdowns, and project updates.

Engineering reads

We scanned gstack. The score was brutal, but the useful part was the verdict.

A real-world scan of gstack showed why AI-slop tooling needs more than a single score. aislop found two confirmed defects, several conservative security patterns, and a large amount of reviewable quality debt. Then we changed the output so teams can see the difference.

Read more →
Guide reads

AI Slop Code Detector: How to Catch Low-Quality AI Code

An AI slop code detector looks for named residue: swallowed exceptions, narrative comments, unsafe casts, dead code. Here is what to detect, what still needs a reviewer, and the workflow that keeps it out of main.

Read more →
Engineering reads

What I fixed after that score, and what I kept

A clean library scored 1 out of 100, and the score was my bug, not the code. Here is the week I spent fixing it: rule by rule, measured on real projects, including the scoring change I built, liked for an hour, and then reverted because it was lying.

Read more →
Opinion reads

The feedback that made my launch

I launched aislop on Hacker News and went from 21 stars to over 200. Then the maintainer of a library with tens of thousands of stars ran it on his own code, scored 1 out of 100, and told me plainly that I had it wrong. That message is the reason I keep building this.

Read more →
Release reads

aislop v0.9.4. SlopCodeBench called it verbosity. We turned it into rules.

Four new Python rules drawn from the verbosity signal in SlopCodeBench (SCBench, arXiv 2603.24755). Plus a CLI star prompt and GitHub Discussions for the community.

Read more →
Release reads

aislop v0.9.3. We measured the noise. Then we cut it by 38%.

Patch release focused on rule precision. Tightens detection across the ai-slop, security, lint, and source-file engines so language conventions are no longer flagged as slop. No new rules — existing ones now discriminate better.

Read more →
Opinion reads

A prompt is a suggestion. A CI gate is a guardrail.

A prompt can guide an agent, but an enforced check is what keeps standards visible in the workflow.

Read more →
Essay reads

The AI Slop Loop: How Code Residue Compounds

Generated output can expand review queues, leave unnecessary code, and weaken team understanding. Learn the evidence-backed loop and how to interrupt it.

Read more →
Reference reads

AI Code Quality Statistics 2026: What the Evidence Shows

Five current studies on AI-authored code, code slop, review capacity, and automated review—plus the limitations teams should understand before quoting them.

Read more →
Guide reads

CodeRabbit vs aislop: AI Review and Deterministic Gates

CodeRabbit combines AI review with 50+ static tools. aislop is a focused deterministic scanner. Compare their overlap, workflows, and tradeoffs.

Read more →