cd /news/ai-agents/hiding-my-ai-slop-from-my-nix-friend… · home › topics › ai-agents › article
[ARTICLE · art-141321] src=fzakaria.com ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Hiding my AI slop from my Nix friends

Developer Farid Zakaria documented a deterministic Python script, tools/check-prose.py, that his AI coding agent created to flag banned words, phrases and em dashes in his source tree, and applied the same check to his own blog posts, finding 21 em dashes and 54 banned words across 91 posts from 2025-2026 versus 0 em dashes and 17 banned words across 64 posts from 2020-2024. Zakaria, who generates his ~/.claude/CLAUDE.md and Codex AGENTS.md agent instructions from agent-settings.nix via home-manager, said the check is verifiable and reproducible unlike a markdown context file. The script fails a repository build on any banned word, phrase, or single em dash and was automatically added to the CI of his omnibin.dev project.

read3 min views1 publishedSep 28, 2026

Warning If you are pissed off reading this, you can start here and work your way back.

I am using AI a lot. I am public about my use of it and when required make the necessary disclosures: “Assited-By” trailers or having to say “I used an AI to help write this software” on every Discourse post.<sup>1</sup>1Seems like whether or not you use AI, I feel more compelled just to disclose I did to avoid the “you didn’t disclose it” argument. Such is life.

For those of you in the “Anti-AI” crowd, it might surprise you to learn that those of us who enjoy using it also don’t want to read “slop”. I also don’t want anything I create to read like I used AI a lot. Commit messages, READMEs, code comments. I’m reading it also!

Being a Nix person, my instructions to the agent are of course declarative. My ~/.claude/CLAUDE.md (and Codex’s AGENTS.md) is generated by home-manager from agent-settings.nix. It has a whole section titled “Writing style: no LLM tells” that I stitched together from Wikipedia’s Signs of AI writing and Simon Willison’s LLM cliche highlighter.

writingStyle = ''
  ## Writing style: no LLM tells

  ### Banned vocabulary

  Do not use these words. They are statistically the loudest signal of
  machine-written text: delve, tapestry, meticulous, pivotal, intricate,
  ...
'';

The code-style tries to ban many AI-isms as they emerge such as: “it’s not X, it’s Y”, “dvelve”, “byte-order”, minimal em-dashes and so forth.

I even came across Fabien Sanglard’s code style rules from this HackerNews thread that I have enjoyed incorporating as well. Why not have my agent write code that mimics engineers I admire!?

Despite this, I still found my agents continuing to use these banned words and phrases. 😒

§Reproducible AI-slop removal #

I was a little annoyed I had to keep re-prompting my preferred writing style but I often reflect on the bitter lesson and generally try to avoid any additional work while I wait for the model’s capabilities to improve.

I was however surprised when upon one such occasion I realized that the agent itself had itself gotten frustrated at forgetting my writing style and turned it into a flake check.

During the creation of omnibin.dev, I noticed the agent had created tools/check-prose.py to check for banned words and phrases in the source tree. It is a simple Python script that walks the repo and fails on a banned word, phrase, or a single em dash anywhere.

I had begun setting up a distinct pattern of how I like my repositories laid out so it was funny to see it automatically include this check in the CI of my build.

Despite the bitter lesson, I might try leveraging this check in my other repos. What I like about deterministic checks rather than a markdown context-file is that it’s verifyable and reproducible. I’m not left guessing whether the agent is following my style or not. I can run the check myself and see if it passes or fails.

§Honesty is a mirror #

Let’s be honest with myself and do some introspection. How much has AI-isms crept into my writing? I applied the same check to my own blog posts.

Years Posts Em dashes Banned words Banned phrases
2020-2024 64 0 17 13
2025-2026 91 21 54 16

Clearly I was not a fan of em dashes in the last five years, then suddenly I found 21 uses in two, which happen to coincide with the proliferation of AI.<sup>2</sup>2The top offender is leverage at 51 hits. I used it in 2021 and 2022 too. Some tells are just mine.  🤔

We seem to be all worried about how many em dashes are in our text. Goodhart’s law teaches us that at that point, that is no longer a good measure of AI slop.

Treat each other kindly.

── more in #ai-agents 4 stories · sorted by recency
── more on @farid zakaria 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/hiding-my-ai-slop-fr…] indexed:0 read:3min 2026-09-28 · —