Ruben Hassid · 18 min read · Gen AI Tools
It's not [X], it's [Y].
Read the original on ruben.substack.com →
The piece claims that AI-generated text often reveals itself through negative parallelism and proposes banning it with a formal anti-ai-writing-style guide. It provides a practical, folder-based workflow (primarily using Claude Cowork) to audit and edit AI outputs to match a desired style, including a downloadable guide and a persistent prompt. It ends with steps to install and enforce the style across projects.
Key Takeaways
- Negative parallelism is a telltale AI-writing pattern and should be banned or auditable in outputs.
- Create an anti-ai-writing-style.md to enforce a consistent, auditable writing style across AI-generated content.
- Use a folder-based workflow (Claude Cowork) with Global Instructions so the AI reads and audits content before producing it.
- Shareable and actionable: provides a downloadable guide and a simple 3-step process to deploy the guide in your environment.
- The approach is adaptable to other AI tools (e.g., ChatGPT) and can be used to standardize long-form content.
Excerpt
If you use this pattern, I instantly know you’re using AI: “It’s not [ thing ], it’s [ other thing ].” Negative parallelism. Forget about it. Ban it. Burn it. Every LLM writes it. Multiple times per response. Barron’s just counted its use in Fortune 500 filings: 50 in 2023, over 200 in 2025. 4x in 2 years (!!!). And even the top guys are (over)using it: Microsoft, McKinsey, Cisco, Accenture, all got caught publishing it this month. The fix is super simple: You create an anti-ai-writing-style.md. file. It’s a single file you upload into your Claude Cowork folder. It…