HN Showcase
Back to browse
Slopsift – a local, graph-backed linter for AI writing

Slopsift – a local, graph-backed linter for AI writing

by NikhilVerma·Jul 18, 2026·1 point·1 comment
Visit ProjectView on HN

AI Analysis

●●●BangerSolve My ProblemBig Brain

Dependency graph parsing beats simple word lists for catching AI slop patterns.

Strengths
  • •Graph-backed NLP detects relationships between words, not just keyword matches.
  • •Runs entirely locally in browser or CLI with zero latency or privacy concerns.
  • •Specific rules for 'negative parallelism' and 'actorless passive voice' are sharp.
Weaknesses
  • •Niche appeal limited to those actively editing AI-generated drafts.
  • •May generate false positives on human writing that mimics LLM cadence.
Target Audience

Writers, editors, and content creators using LLMs

Similar To

Grammarly · Hemingway App · Originality.ai

Post Description

SlopSift uses NLP-backed lint rules. It goes beyond word lists and part-of-speech tags by matching relationships in a dependency graph. Though it still includes a few word-based rules for tells like “delve” and, most recently, “load-bearing.”

It’s deterministic and runs locally, in your browser or from the CLI.

Similar Projects