Why Better Writing Matters for Developers in the Age of AI Slop

X postGergely OroszOpinion

Gergely Orosz has made his previously paywalled guide on professional writing freely available to counter low-quality AI-generated content. He argues that writing is thinking and remains essential for career progression in software engineering. The piece provides actionable advice on drafting, editing, and feedback.

Key points

  1. Orosz argues writing is thinking, viewing AI as dull for core writing tasks while noting it remains effective for summarisation.
  2. Companies including Amazon, Stripe, and TrueLayer include writing exercises in hiring screens for senior engineering roles.
  3. Software developers in high-growth companies frequently write more words daily in reviews, PRDs, and chats than actual code.
  4. Effective writing relies on separating the workflow into three steps: drafting, editing for clarity, and collecting feedback.
  5. He highlights the book 'Writing for Developers' by Piotr Sarna and Cynthia Dunlop for practical guidance.

Why it matters

As remote engineering workflows expand, written influence across teams determines seniority, making authentic and clear communication more valuable than automated drafts.

Analysis

Writing as a Career Differentiator

In distributed tech organisations, written communication is essential for scaling influence beyond immediate teams. Gergely Orosz notes that senior individual contributors and managers produce high volumes of written artefacts daily, ranging from design proposals and postmortems to code reviews and peer assessments. Top tech firms like Stripe, Amazon, and TrueLayer increasingly integrate written evaluations into their senior and leadership hiring processes.

The Issue with Generative AI in Technical Writing

Orosz decided to ungate this article after observing developers relying on AI tools to produce shallow, generic content. Echoing Steven Sinofsky's tenet that "writing is thinking," Orosz warns that offloading composition harms critical clarity. In his experience, AI struggles with original technical thinking and causes frustration when used for anything beyond summarising existing material.

The Mechanics of Clear Technical Prose

The guide breaks down high-quality technical writing into three distinct stages: drafting raw thoughts, rigorous editing to remove clutter, and gathering review feedback. Rather than attempting polished prose on the first pass, developers should focus on capturing facts, refining phrasing subsequently, and reading well-crafted engineering materials to build their writing habits over time.

Original post

Gergely Orosz

@GergelyOrosz · 30 October 2026

Made the previously paid article "Becoming a better writer" free. I see too many devs writing low quality slop with AI. Hopefully this helps those of you who want to share more of your own experiences, using your own words - we need more of these! t.co/nk5OzsS93n t.co/62fEcEJHhF

1.6k likes78 replies2.1k bookmarks99.6k views

View on X
More posts in the thread (2)
  1. @CoderRw11326 Experiment what works for you! I’m still in the camp that writing is thinking and AI is particularly dull at this, and I only get frustrated when I use it for anything but summarization (that it’s good at)
  2. @joshva_jebaraj ah thank you! He closed his website haha since becoming pretty much fulltime editing on The Pragmatic Engineer since, let me remove it
Selected replies (5)
  • @CoderRw11326 @GergelyOrosz This is great! Do u recommend doing all the write by ourselves, or it’s fine to get some draft with AI(not creat the full slop with it)?
  • @0xcgn @GergelyOrosz bookmarked. writing is one of the things that i really suck at and been trying to improve
  • @growingwise2026 @GergelyOrosz For many non-native English speakers, AI helps us express ideas we already have but may struggle to put into words. What matters most is critical thinking, original ideas, and direction, AI can assist with writing, but the vision still comes from us.
  • @joshva_jebaraj @GergelyOrosz Hey @GergelyOrosz Thanks for sharing the awesome article small nitpicking the link for the Dominic Grover in the article seems broken t.co/XVt0ovx7Ng
  • @Hussein__khidr @GergelyOrosz Free article about avoiding slop. Great, now it's training data

Mentioned links

Links and tools from this entry

Summary generated by AI (Gemini 3.8 Flash, 2 November 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:Gergely Orosz

    Becoming a Better Writer in Software Engineering and Leadership

    Clear writing is an essential skill for software engineers and engineering managers aiming for career growth. Gergely Orosz shares actionable techniques for drafting, editing, and refining technical communications.

    Web development· Resource

  • X post:Gergely Orosz

    Free O'Reilly E-Book: Scaling AI Adoption in Engineering

    Gergely Orosz highlighted an in-progress O'Reilly e-book by Peter Bell titled 'Scaling AI Adoption in Engineering'. Offered for free as an Early Release sponsored by Antithesis, the guide aims to help CTOs and engineering leaders deliver tangible business value through AI.

    2.6kbookmarks148.9kviews

    AI & LLMs· Resource

  • Article:Peter Yang

    Open-Source Skill to Strip AI Slop and the 25/50/25 Rule for Writing

    Peter Yang has open-sourced an AI skill called /no-ai-slop for harnesses like Claude Code and Codex. The tool detects and removes over 20 repetitive patterns commonly produced by generative models. Alongside the release, Yang outlines a 25/50/25 writing process to retain editorial control.

    AI & LLMs· Tool

  • X post:Ren

    no-ai-slop: Tool to Remove AI-Generated Writing Habits

    An X post highlights the open-source project no-ai-slop, designed to strip characteristic AI writing patterns from articles. The repository gathered more than 7,700 GitHub stars within two months.

    777bookmarks33.6kviews

    AI & LLMs· Tool

  • Link:Peter G. Yang

    No AI Slop: An Agent Skill for Eliminating AI Writing Patterns

    Peter G. Yang has released an agent skill designed to identify and remove AI cliches from writing. It acts as an editor to make drafts clearer and more engaging while preserving the author's distinctive voice.

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.