{"slug": "why-is-ai-slop-so-frustrating-to-read", "title": "Why is AI slop so frustrating to read?", "summary": "Zhizhuo (Z) Zhou reported on X that a benchmark from zonderlabs.com found AI writing violates established English writing principles far more often than human writing, with Claude Code replies \"by far the worst offenders.\" Zhou identified three recurring slop patterns: hidden characters and actions where the main character and action are not the sentence's subject and verb, awkward noun-chained word choice such as \"a label's awareness entry\" and \"vision-and-transcript pass,\" and a lack of prioritization that leaves sentences devoid of meaning or loaded with distracting points. Zhou argued the issue matters because most internet content is AI generated and technical communication must stay clear for humans to understand.", "body_md": "Zhizhuo (Z) Zhou on X: \"Why is AI slop so frustrating to read?\nAI writing often obscures main ideas and invents awkward phrases, making sentences more complex than necessary.\nMany of these slop patterns violate writing principles established in English writing books.\nIn our benchmark, AI writ… / X\n\nZhizhuo (Z) Zhou on X: \"Why is AI slop so frustrating to read?\nAI writing often obscures main ideas and invents awkward phrases, making sentences more complex than necessary.\nMany of these slop patterns violate writing principles established in English writing books.\nIn our benchmark, AI writing breaks these principles far more often than human writing, with Claude Code replies by far the worst offenders.\nWe show examples of the most common slop patterns in this thread\"\n\nWhy is AI slop so frustrating to read?\nAI writing often obscures main ideas and invents awkward phrases, making sentences more complex than necessary.\nMany of these slop patterns violate writing principles established in English writing books.\nIn our benchmark, AI writing breaks these principles far more often than human writing, with Claude Code replies by far the worst offenders.\nWe show examples of the most common slop patterns in this thread\n\nWhy is AI slop so frustrating to read?\nAI writing often obscures main ideas and invents awkward phrases, making sentences more complex than necessary.\nMany of these slop patterns violate writing principles established in English writing books.\nIn our benchmark, AI writing breaks these principles far more often than human writing, with Claude Code replies by far the worst offenders.\nWe show examples of the most common slop patterns in this thread\n\nThe most jarring slop pattern of AI writing is hidden characters and actions. This happens when the main character and action of a sentence are not the subject and verb.\nSee how the same story of \"a duck (main character) walked up and asked (main action)\" can be written in an unclear way. 2/5\n\nAnother common AI slop pattern is awkward and confusing word choice. AI models have a tendency to chain together nouns into unnatural expressions.\nSome in the wild examples include \"a label's awareness entry,\" \"vision-and-transcript pass,\" and \"length floor drops a block.\" 3/5\n\nFinally, AI writing often has no prioritization of the points it wants to make. This results in sentences that are devoid of meaning or sentences that have multiple distracting points. 4/5\n\nThis writing stuff matters because the majority of the internet we consume is AI generated. And as work, research, and technical communication become increasingly AI generated, we must make sure that AI communicates clearly in a way that us, humans, can understand.\nRead more about slop and explore interactive demos on our web page zonderlabs.com/slop\nAnd if you vibe with our mission, please reach out!\n\nHave you found any mitigations? Genuinely, which ever lab solves this will have my subscription forever. Every time I have to read dense claudish it makes my eyes twitch. Too much and I start to feel nauseous", "url": "https://wpnews.pro/news/why-is-ai-slop-so-frustrating-to-read", "canonical_source": "https://twitter.com/zhizdev/status/2119874095269707977", "published_at": "2026-11-10 00:52:01+00:00", "updated_at": "2026-11-10 01:23:06.055708+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "generative-ai", "ai-research"], "entities": ["Zhizhuo (Z) Zhou", "Claude Code", "X", "Zonder Labs"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/why-is-ai-slop-so-frustrating-to-read", "markdown": "https://wpnews.pro/news/why-is-ai-slop-so-frustrating-to-read.md", "text": "https://wpnews.pro/news/why-is-ai-slop-so-frustrating-to-read.txt", "jsonld": "https://wpnews.pro/news/why-is-ai-slop-so-frustrating-to-read.jsonld"}}