{"slug": "a-self-evident-essay-arguing-for-the-use-of-ai-in-writing", "title": "A Self-Evident Essay Arguing for the Use of AI in Writing", "summary": "A writer documented using Anthropic's Claude Code to draft and revise an essay arguing for AI in writing, reporting that Claude raised 12 structure issues in one run, of which 9 were accepted as suggested, 2 were accepted with edits, and 1 piece of advice was followed. The author also used Claude-generated Vim functions built on tpope/vim-dispatch and configured the prettier tool for a one-sentence-per-line format to make commit differences easier to inspect. Claude additionally flagged a lack of parallelism in the section headings, leading to two subtitles being updated.", "body_md": "This little project is meant to argue for the use of AI, and to demonstrate the\nuse of AI in the process of forming the argument itself.\nIt is best to inspect the commit differences with the `--word-diff` flag.\n\nEssay: [The Sins of AI Writing](https://github.com/Sheer-Economics/the-sins-of-AI-writing/blob/master/20260920-the_sins_of_AI_writing.md)\nPrompts: [Claude Code Prompt](https://github.com/Sheer-Economics/the-sins-of-AI-writing/blob/master/.claude/essay.md)\n\nThe draft was written quickly, after thinking about the issue for one evening.\n\nAfter the draft, I needed a plugin for the Vim editor to hook into Claude Code.\nNone existed off-the-shelf, so I talked to Claude and settled on using\n`tpope/vim-dispatch` with some Claude-generated Vim functions.\n\nIt was done paragraph by paragraph. The process was slow because I wouldn't let go of the opportunity to learn from fixing those grammar errors.\n\nWhen the first half of the essay was done, I started to rewrite the second half, realizing it was poorly constructed.\n\nI set out to configure the tool `prettier` with a plugin to enable a\none-sentence-per-line format, so that the differences between commits could be\neasily inspected.\n\nI fixed grammar errors in the second half of the essay.\n\nThen, I felt the example in the last section might not be well received. Despite being a genuine personal example, it could spark an unnecessary, off-topic argument about ad promotion. I flagged it to rewrite later.\n\nClaude raised 12 structure issues in one run. Of these, 9 were accepted as suggested, 2 were accepted with edits, and 1 piece of advice was followed.\n\nIt also flagged a lack of parallelism in the section headings. As a result, two subtitles were updated.\n\nI replaced it with a general example, as flagged previously.\n\nAI made it very easy.", "url": "https://wpnews.pro/news/a-self-evident-essay-arguing-for-the-use-of-ai-in-writing", "canonical_source": "https://github.com/Sheer-Economics/the-sins-of-AI-writing", "published_at": "2026-09-22 10:28:56+00:00", "updated_at": "2026-09-22 10:54:33.069769+00:00", "lang": "en", "topics": ["ai-tools", "generative-ai", "large-language-models", "ai-products"], "entities": ["Claude Code", "Anthropic", "Vim", "tpope/vim-dispatch", "prettier"], "alternates": {"html": "https://wpnews.pro/news/a-self-evident-essay-arguing-for-the-use-of-ai-in-writing", "markdown": "https://wpnews.pro/news/a-self-evident-essay-arguing-for-the-use-of-ai-in-writing.md", "text": "https://wpnews.pro/news/a-self-evident-essay-arguing-for-the-use-of-ai-in-writing.txt", "jsonld": "https://wpnews.pro/news/a-self-evident-essay-arguing-for-the-use-of-ai-in-writing.jsonld"}}