<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/write-drunk-edit-sober-creating-generative-content-responsibly---matthijs-van-der-veer-66jegrufo" -->

---
title: Write Drunk, Edit Sober: Creating Generative Content...
description: A conference talk transcript arguing against uncritical use of LLMs for writing, coining the approach 'write drunk, edit sober.' The speaker identifies...
canonical: https://daily.dev/posts/write-drunk-edit-sober-creating-generative-content-responsibly---matthijs-van-der-veer-66jegrufo
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Write Drunk, Edit Sober: Creating Generative Content Responsibly - Matthijs van der Veer | daily.dev
og:description: A conference talk transcript arguing against uncritical use of LLMs for writing, coining the approach 'write drunk, edit sober.' The speaker identifies...
og:url: https://daily.dev/posts/write-drunk-edit-sober-creating-generative-content-responsibly---matthijs-van-der-veer-66jegrufo
og:image: https://api.daily.dev/og/posts/66jegrUfO.png
og:image:alt: Write Drunk, Edit Sober: Creating Generative Content Responsibly - Matthijs van der Veer
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Write Drunk, Edit Sober: Creating Generative Content Responsibly - Matthijs van der Veer

**[NDC Conferences](https://daily.dev/sources/ndc)** · 56 min read · 0 upvotes · 0 comments

## Summary

A conference talk transcript arguing against uncritical use of LLMs for writing, coining the approach 'write drunk, edit sober.' The speaker identifies telltale signs of AI-generated content (em dashes, emojis, bold text, words like 'delve' and 'in an era'), explains the psychology of automation bias, and demonstrates a GitHub-based tool called Mandrean Muse that generates conference abstracts from structured intent prompts, then uses deterministic NLP (spaCy lemmatization) and a tropes-based checker (Slop Slurp) to flag AI slop patterns. Key argument: intent must come first, LLMs diffuse rather than concentrate meaning, and developers should use deterministic code over LLM recommendations wherever possible to preserve authenticity.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.youtube.com/watch?v=e4Ig3w1dG-8>

## Similar posts on daily.dev

- [Is This Slop? Detecting AI-Generated Content Without a Model](https://daily.dev/posts/is-this-slop-detecting-ai-generated-content-without-a-model-bn7hlke8u) · Towards Data Science · 1 upvotes · 0 comments
- [Content for Content’s Sake](https://daily.dev/posts/content-for-content-s-sake-uyky4wedd) · Armin Ronacher · 13 upvotes · 0 comments
- [Sid's Blog](https://daily.dev/posts/sid-s-blog-llgej3cax) · Hacker News · 1 upvotes · 0 comments
- [Take Back the EM Dash — and Your Voice](https://daily.dev/posts/take-back-the-em-dash-and-your-voice-wy1iaq27f) · Atomic Spin · 4 upvotes · 0 comments
- [AI Forces You to Commit to Your Initial Belief](https://daily.dev/posts/ai-forces-you-to-commit-to-your-initial-belief-z9d2cpnfu) · Ibrahim Diallo · 0 upvotes · 0 comments

---

Tags: [#llm](https://daily.dev/tags/llm), [#nlp](https://daily.dev/tags/nlp), [#prompt-engineering](https://daily.dev/tags/prompt-engineering)

[View this post on daily.dev](https://daily.dev/posts/write-drunk-edit-sober-creating-generative-content-responsibly---matthijs-van-der-veer-66jegrufo)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Write Drunk, Edit Sober: Creating Generative Content Responsibly - Matthijs van der Veer","url":"https://daily.dev/posts/write-drunk-edit-sober-creating-generative-content-responsibly---matthijs-van-der-veer-66jegrufo","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/write-drunk-edit-sober-creating-generative-content-responsibly---matthijs-van-der-veer-66jegrufo"},"datePublished":"2026-08-05T09:32:22.512Z","dateModified":"2026-08-05T09:32:43.657Z","description":"A conference talk transcript arguing against uncritical use of LLMs for writing, coining the approach 'write drunk, edit sober.' The speaker identifies...","image":"https://i.ytimg.com/vi/e4Ig3w1dG-8/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/e4Ig3w1dG-8/sddefault.jpg","isAccessibleForFree":true,"articleSection":"NDC Conferences","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"NDC Conferences","logo":"https://media.daily.dev/image/upload/s--SiIyojEj--/f_auto/v1748760369/logos/ndc","url":"https://daily.dev/sources/ndc"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/write-drunk-edit-sober-creating-generative-content-responsibly---matthijs-van-der-veer-66jegrufo","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,nlp,prompt-engineering","timeRequired":"PT56M","video":{"@type":"VideoObject","name":"Write Drunk, Edit Sober: Creating Generative Content Responsibly - Matthijs van der Veer","description":"A conference talk transcript arguing against uncritical use of LLMs for writing, coining the approach 'write drunk, edit sober.' The speaker identifies...","thumbnailUrl":"https://i.ytimg.com/vi/e4Ig3w1dG-8/sddefault.jpg","uploadDate":"2026-08-05T09:32:22.512Z","duration":"PT56M","url":"https://api.daily.dev/r/66jegrUfO","embedUrl":"https://www.youtube.com/embed/e4Ig3w1dG-8"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NDC Conferences","item":"https://daily.dev/sources/ndc"},{"@type":"ListItem","position":3,"name":"Write Drunk, Edit Sober: Creating Generative Content Responsibly - Matthijs van der Veer"}]}
```

