--- title: Write for people | daily.dev description: An engineer reflects on how AI-generated PR titles, descriptions, and documentation are becoming increasingly unreadable, filled with jargon and verbose filler... canonical: https://daily.dev/posts/write-for-people-wfatmufup twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Write for people | daily.dev og:description: An engineer reflects on how AI-generated PR titles, descriptions, and documentation are becoming increasingly unreadable, filled with jargon and verbose filler... og:url: https://daily.dev/posts/write-for-people-wfatmufup og:image: https://api.daily.dev/og/posts/wFATMuFUp.png og:image:alt: Write for people 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 for people **[Lobsters](https://daily.dev/sources/lobsters)** · 3 min read · 1 upvotes · 0 comments ## Summary An engineer reflects on how AI-generated PR titles, descriptions, and documentation are becoming increasingly unreadable, filled with jargon and verbose filler that mimics understanding without conveying it. The piece argues that jargon can be a useful shortcut among peers but becomes harmful when machine-generated text targets people at varying levels of understanding without real compression of ideas. It calls for writing with clarity and simplicity, suggesting that if something can't be explained simply, the underlying problem may not yet be fully understood, and that people should strive to be 'more tired than the model' rather than offloading that effort into bloated auto-generated text. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community take How the wider developer community reacted, aggregated from 1 discussion and 10 comments across lobsters (as of 2026-09-14). **TL;DR:** Discussion mostly centers on practical ways to handle LLM-generated PR descriptions (like hiding them in collapsible widgets) rather than disputing the post's core argument, with a side debate breaking out over site tagging conventions for AI-related posts. **Sentiment:** 20% positive · 55% mixed · 25% skeptical **The case for** - Collapsing LLM-generated text behind a details/summary widget preserves useful information without cluttering the review with an impersonal wall of text. - Generated descriptions can still hold value for future coding-agent context even if humans don't read them closely. **The pushback** - Deleting the LLM draft after distilling it yourself could be seen as dishonest versus just hiding it. - Generated PR descriptions often add little beyond what's already visible in the diff, making the distillation step feel pointless. - Leaving distillation work to each reviewer individually just shifts the burden rather than solving it. **By community** - lobsters (mixed): Commenters largely agree PR description slop is a real problem and swap practical fixes, while a side argument flares up over whether the site's 'vibecoding' tag is used fairly. **Hottest debate:** Whether deleting an LLM-generated draft after distilling it is more honest than simply hiding it behind a collapsed widget, and separately whether the 'vibecoding' tag unfairly singles out AI-related posts. **Open questions** - Would reviewers ever actually read the collapsed LLM-generated text if given the option? - Does keeping the raw LLM description around (even hidden) help or hurt future coding-agent performance? **Highlights** > Something I've started doing recently that I feel pretty good about is hiding the LLM-generated PR in a `

` collapsed widget and adding my own short human-written description outside of that. Here's a recent example: https://github.com/datasette/datasette-apps/pull/22 The LLM descriptions have useful information in them but they're also an impersonal wall of text. > — [simonw on lobsters · 1 points, 2 comments](https://lobste.rs/s/0fokml/write_for_people#c_hfhlhy) > What would be really helpful to your reviewers would be if you could read the LLM output and distill it yourself, into your own words, and then delete the LLM's version, and leave only the pertinent part for the reviewers instead of leaving the distillation task as something each of them needs to do individually. This would probably help you better understand the code that you are presenting for review, as well. > — [gigawhitlocks on lobsters · 5 points, 2 comments](https://lobste.rs/s/0fokml/write_for_people#c_mwm4mc) > I do think it's justified here: > But where it starts to get dicey is when you have both jargon and long text explanations being generated by machines, for people at different levels of understanding. Or a more cynical take: Lobste.rs is a website about software development, and software development is increasingly inseparable from the use of coding agents - either because people use them, or because people make a point of *not* using them. The Lobste.rs decision to tag anything relating to LLMs with "vibecoding" increasingly means that almost every article about writing software will have that tag. (Imagine a software development forum that insisted every post that involves an IDE was tagged "lol-dumbass-ide-users".) > — [simonw on lobsters · 2 points, 1 comments](https://lobste.rs/s/0fokml/write_for_people#c_jypc1l) > Is it really better for people if I distill information and then delete it, as opposed to distilling information but leaving the original available but hidden behind an expand widget? Deleting the original feels dishonest to me. (I'm usually not distilling from the LLM-version at all though, the commentary I leave is meant to be of a different nature entirely from the concrete here's-what-is-in-the-change text.) > — [simonw on lobsters · 1 points, 1 comments](https://lobste.rs/s/0fokml/write_for_people#c_qjfhdh) **Source threads** - [lobsters](https://lobste.rs/s/0fokml/write_for_people) · 13 points · 10 comments ## Similar posts on daily.dev - [Do people still genuinely care about technical articles ?](https://daily.dev/posts/do-people-still-genuinely-care-about-technical-articles--xjdribzgj) · DEV · 6 upvotes · 2 comments - [Technical Writing in the AI Age](https://daily.dev/posts/technical-writing-in-the-ai-age-8nv7rdfjb) · CSS-Tricks · 58 upvotes · 4 comments - [Say No To AI Prose: Humans Should Write For Humans, Not LLMs](https://daily.dev/posts/say-no-to-ai-prose-humans-should-write-for-humans-not-llms-lrfziqfpl) · ElixirStatus · 0 upvotes · 0 comments --- Tags: [#career](https://daily.dev/tags/career), [#llm](https://daily.dev/tags/llm), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/write-for-people-wfatmufup) ```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 for people","url":"https://daily.dev/posts/write-for-people-wfatmufup","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/write-for-people-wfatmufup"},"datePublished":"2026-08-14T21:52:31.419Z","dateModified":"2026-09-14T06:05:12.451Z","description":"An engineer reflects on how AI-generated PR titles, descriptions, and documentation are becoming increasingly unreadable, filled with jargon and verbose filler...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/221c86f89097cfffd5bd5d5224cec3ee?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/221c86f89097cfffd5bd5d5224cec3ee?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Lobsters","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":"Lobsters","logo":"https://media.daily.dev/image/upload/s--tl8v_Fku--/f_auto,t_logo/v1698841318/logos/lobste.jpg","url":"https://daily.dev/sources/lobsters"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/write-for-people-wfatmufup","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"career,llm,code-review","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Lobsters","item":"https://daily.dev/sources/lobsters"},{"@type":"ListItem","position":3,"name":"Write for people"}]} ```