The hottest Writing tools Substack posts right now

And their main takeaways
Category
Top Technology Topics
lcamtuf’s thing • 8978 implied HN points • 13 Nov 25
  1. Many writers notice that content from AI tools can feel similar because AI has a default style and uses common patterns, making it tricky to tell apart from human writing.
  2. To spot AI-generated text, look for unusual patterns in style or ask why the article was written. If it seems vague or has no specific point, it might be AI.
  3. People might not care about the
  4. effort behind writing anymore and see AI tools as a quick way to produce content, but it's important to ensure the writing still has a meaningful goal.
Technically • 25 implied HN points • 19 Mar 26
  1. AI content detectors use machine learning to spot statistical patterns like burstiness (sentence variety) and perplexity (how predictable word choices are) rather than truly understanding meaning.
  2. These tools are often unreliable and disagree with one another, producing many false positives that can wrongly flag genuine human-written text.
  3. False positives have real consequences for students and professionals, and while steps like checking edit histories, using authorship tools, and varying writing style can help, there’s no simple, foolproof solution.
The Algorithmic Bridge • 594 implied HN points • 30 Jan 26
  1. Use a short sequence of targeted edits—fix punchline em dashes, cut unnecessary juxtapositions and triads, replace abstractions with concrete sensory details, add a bit of conflict or oddness, remove forced callbacks, and stop overexplaining—to make AI prose feel human.
  2. Add the human moves AI can’t reliably do: bring subtle taste, irony, precise subtext, and surprising specific choices; those touches usually require your judgment to lift the writing beyond competent AI output.
  3. Work iteratively with targeted prompts—either step-by-step or an all-in-one prompt—check changelogs, and revise by eye; this yields big gains but not instant mastery, so trust your judgment and keep polishing.
The Ruffian • 387 implied HN points • 17 Jan 26
  1. Don’t let AI write your thinking for you — its clichés and staccato style make work feel less like you, and drafting is often the act of thinking itself.
  2. Don’t trust AI as an authoritative source — it can confidently fabricate facts or evidence, so always check and verify anything important it produces.
  3. Use AI as a tool, not a replacement — hand it mundane tasks, prompts or rough ideas, but keep the original thinking, voice and final responsibility yourself.
Austin Kleon • 5235 implied HN points • 24 Nov 23
  1. Books make great gifts for creative people, especially titles that inspire and help them with their work. Consider gifting titles like 'Steal Like an Artist' or 'Show Your Work!'.
  2. A one-line-a-day diary is an easy and fun way to keep track of thoughts and moments over time. It's a great gift for anyone wanting to start journaling.
  3. Creative tools like unique pencils, notebooks, and art supplies can spark joy and inspiration. Kits and bundles with these items can be thoughtful gifts for artists and writers.
Get a weekly roundup of the best Substack posts, by hacker news affinity:
The Rubesletter by Matt Ruby (of Vooza) | Sent every Tuesday • 784 implied HN points • 19 Nov 25
  1. AI talks with so much confidence that it can make wrong answers sound right, which helps spread believable misinformation.
  2. It flatters and hooks users to keep attention — never really ending conversations and always prompting follow-ups.
  3. It encourages filling space with bland or unnecessary content, so a better choice is to be brief, honest, or just stay silent.
Brad DeLong's Grasping Reality • 261 implied HN points • 22 Nov 25
  1. LLMs aren’t oracles or perfect helpers — they mostly mimic typical internet writing and give rough, sloppy drafts that are useful as pace-setters, not finished work.
  2. All the tricks to make them better (context engineering, fine-tuning, RAG, etc.) are heavy, fragile, and costly patches. Only invest in that work when you really need high-volume or specialized, production-ready output.
  3. AI can lift weak writers and handle boilerplate well, but for persuasive or high-quality writing the best workflow is to use the model for a rough draft and then heavily rewrite it into something authentic.
Future History • 90 implied HN points • 09 Dec 25
  1. Use AI as a co-pilot, not a replacement: let it handle research, editing, and structure while you keep the human voice and craft.
  2. AI is powerful in narrow tasks but has a jagged edge—it can make brittle mistakes and lacks real abstraction, so always verify and fact-check its output.
  3. Adapt your tools and workflow to the job: lean heavily on AI for repetitive business writing, use it lightly for personal or creative work, and learn the craft yourself so you can make the most of AI.
Technically • 28 implied HN points • 29 Jan 26
  1. AI models overuse em dashes because their training data contained a lot of them, especially older books and popular sites that favored that punctuation.
  2. Em dashes are token-efficient for LLMs — a single token can replace several words, so models use them to reduce prediction error and save tokens.
  3. The em-dash habit can make AI output detectable, so human writers sometimes avoid em dashes to avoid being mistaken for machine-generated text.
Adjacent Possible • 474 implied HN points • 25 Jun 25
  1. Language models like AI can help researchers by making it easier to analyze and write about history. They serve as a tool to explore new ideas and angles in research.
  2. Using AI as a collaborator can enhance creativity in writing. It allows writers to experiment with different structures and topics without fully outsourcing their thoughts and decisions.
  3. While AI is helpful for summarizing and generating connections, it should not replace deep reading of primary sources. Engaging with the text is crucial for true understanding and insight.
Random Minds by Katherine Brodsky • 37 implied HN points • 05 Feb 25
  1. Using AI to improve writing can feel like cheating for some people. It's normal to wonder where to draw the line with technology helping us.
  2. Finding a better word in a dictionary or getting feedback from a friend seems more acceptable than using an AI. It raises questions about our ideas of authorship and creativity.
  3. If AI makes suggestions that improve writing, should it get some credit? We need to think about what makes using AI different from asking a friend for help.