<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/1G9kVUOJq" -->

---
title: "A" for "Average" | daily.dev
description: The author argues that being impressed by AI-generated code in an unfamiliar language says more about the reader's own ignorance of that domain than about AI's...
canonical: https://daily.dev/posts/a-for-average--1g9kvuojq
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: "A" for "Average" | daily.dev
og:description: The author argues that being impressed by AI-generated code in an unfamiliar language says more about the reader's own ignorance of that domain than about AI's...
og:url: https://daily.dev/posts/a-for-average--1g9kvuojq
og:image: https://api.daily.dev/og/posts/1G9kVUOJq.png
og:image:alt: "A" for "Average"
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.

# "A" for "Average"

**[stitcher.io](https://daily.dev/sources/stitcher)** · 2 min read · 10 upvotes · 5 comments

## Summary

The author argues that being impressed by AI-generated code in an unfamiliar language says more about the reader's own ignorance of that domain than about AI's actual competence. Since LLMs work by predicting the statistically most likely next token, their output is, by design, average — not exceptional. Feeling awed by AI output in an unfamiliar language is compared to being fooled by a magic trick you don't understand, while the same average quality in a familiar language is correctly perceived as merely adequate.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://stitcher.io/blog/a-for-average>

## Community discussion

Top comments from developers on daily.dev.

**@feforeboot** · 0 upvotes

> Yes, I too often win imaginary arguments when I get to set the criteria at my argument's convenience.
>
> Most useful production code isn't innovative or remarkable. It just needs to work, be readable, and follow conventions, which is exactly what "average" means.
>
> Kind of ironic that an LLM would catch this fallacy immediately.

**@agustinbarrientos** · 0 upvotes

> I suspect cross-language agent work gets much safer when a maintainer from the target ecosystem writes the acceptance test. Generic checks can miss idioms and unsafe defaults that look normal from outside.

## Similar posts on daily.dev

- [Settle down, nerds. AI is a normal technology](https://daily.dev/posts/settle-down-nerds-ai-is-a-normal-technology-p56vrjsqy) · Stack Overflow Blog · 6 upvotes · 0 comments
- [I can never fully embrace LLMs for code](https://daily.dev/posts/i-can-never-fully-embrace-llms-for-code-aw1v4ccnc) · Ibrahim Diallo · 15 upvotes · 3 comments
- [Are We Having the Wrong AI Dreams?](https://daily.dev/posts/are-we-having-the-wrong-ai-dreams--yepeegu0r) · JetBrains · 2 upvotes · 0 comments

---

Tags: [#ai](https://daily.dev/tags/ai), [#llm](https://daily.dev/tags/llm), [#ai-coding](https://daily.dev/tags/ai-coding)

[View this post on daily.dev](https://daily.dev/posts/a-for-average--1g9kvuojq)

```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":"\"A\" for \"Average\"","url":"https://daily.dev/posts/a-for-average--1g9kvuojq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/a-for-average--1g9kvuojq"},"datePublished":"2026-08-24T13:56:19.652Z","dateModified":"2026-09-13T21:59:42.656Z","description":"The author argues that being impressed by AI-generated code in an unfamiliar language says more about the reader's own ignorance of that domain than about AI's...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8ae75ade6d9e7d6c438d57caf3bbc736?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8ae75ade6d9e7d6c438d57caf3bbc736?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"stitcher.io","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":"stitcher.io","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/83a32fc89f9943f38951a2b360c0d3ec","url":"https://daily.dev/sources/stitcher"},"commentCount":5,"discussionUrl":"https://daily.dev/posts/a-for-average--1g9kvuojq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":10},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":5}],"keywords":"ai,llm,ai-coding","timeRequired":"PT2M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"stitcher.io","item":"https://daily.dev/sources/stitcher"},{"@type":"ListItem","position":3,"name":"\"A\" for \"Average\""}]}
{"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/a-for-average--1g9kvuojq","comment":[{"@type":"Comment","text":"Yes, I too often win imaginary arguments when I get to set the criteria at my argument’s convenience.\nMost useful production code isn’t innovative or remarkable. It just needs to work, be readable, and follow conventions, which is exactly what “average” means.\nKind of ironic that an LLM would catch this fallacy immediately.","datePublished":"2026-08-24T20:38:49.820Z","url":"https://daily.dev/posts/1G9kVUOJq#c-QBmt67rwq","author":{"@type":"Person","name":"FG","url":"https://daily.dev/feforeboot","image":"https://media.daily.dev/image/upload/s--O0TOmw4y--/f_auto/v1715772965/public/noProfile"}},{"@type":"Comment","text":"I suspect cross-language agent work gets much safer when a maintainer from the target ecosystem writes the acceptance test. Generic checks can miss idioms and unsafe defaults that look normal from outside.","datePublished":"2026-08-27T20:06:53.989Z","url":"https://daily.dev/posts/1G9kVUOJq#c-G3l3Oz19a","author":{"@type":"Person","name":"Agustin Barrientos","url":"https://daily.dev/agustinbarrientos","image":"https://media.daily.dev/image/upload/s--5ayxQnqn--/f_auto/v1788281802/avatars/avatar_wQYYVe5Tbj0NJ7C7qPoa8?_a=BAMAMicg0"}}]}
```

