Vibe writing maxims

02 May 2025

Shreyas Prakash headshot

Shreyas Prakash

Some vibe-writing maxims:

  • While writing, have two windows open: one for the writing, and the other one for ChatGPT. Previously I used to consult ChatGPT a couple of times for internet research, but now the role has transitioned to be a more conversational thought partner, helping you riff-raff on the idea for the essay. (Let’s say you’re writing an essay about tarrifs, and you want to understand what the general consensus is, so that you could provide an unique insight that can counter-position to the general consensus. It’s particularly helpful to provide this). Deep Research is also effective in productizing the ‘secondary research’ part of any essay where you have to crawl all over the internet to then derive the analysis from (Deep Research is basically a Mckinsey level research analyst at your doorstep helping you with this part of the process)
  • It also helps with alternative word seeking. Let’s say we want to find an alternate word to “outrage”, and you can give some references to ground them so that it generates a close cousin you’re expecting. This can be done on a word level, sentence level, or even on a paragraph level.
  • AI can help in fleshing out the essay with a meta-analysis, your first pass roughest-rough draft (even half-way through), you could probe ChatGPT to analyse if you’re getting to the core of the argument quickly? is it building momentum? is it a good opening, or there could be some alternate openings, closings?
  • In essays which involve more argument analysis, I also apply some of these questions inspired by Lex Fridman’s interview style. For eg:
QuestionPurpose
Can you steelman the case for …?Elicit strongest argument for..
Can you strawman the case for..?Address counterarguments for..
Can we break this down into first principles…Analyse from basic axioms
What happens if we take this to the extremes..Test robustness when it comes to the edge cases
  • The more we use AI-assisted writing, there is a big risk of the writing sounding like AI. The line needs to be tread carefully where you use AI for asking good questions, identify flaws, improve/edit content, not to actually put words in your mouth. I also use this quite extensively to remove the filler words such as dwelve, em-dashes and the usual AI-generated copypasta: `Identify and remove any generic or overused phrases that make the writing sound artificial. Replace common AI phrases with more original, specific language.

Subscribe to get future posts via email (or grab the RSS feed). 2-3 ideas every month across design and tech

Read more

  1. 18 key ideas from reading Henrik Karlsson this monthwriting
  2. Stop arguing, and start drawing circles togethermathematics
  3. The whole world is just the snake eating its own tailmental-models
  4. Life lessons and hot takes from my 30slifestyle
  5. Building a skill for coherent science illustrationsscience
  6. My agentic engineering workflow (step by step)agentic-coding
  7. Hammock driven developmentagentic-coding
  8. Peculiar ways number three fits into our funny little brainsmental-models
  9. AI sandwich as a defacto principle for anything agentic engineering relatedagentic-coding
  10. Authority in the guise of evidencecritical-rationalism
  11. Map is not the territoryphilosophy
  12. Self hypnosis as a manifestation ritualmeditation
  13. Hegelian dialectic for structured reasoning with AI agentsphilosophy
  14. How I prepare for tough negotiations nowadaysnegotiation
  15. When should we steelthread somethingproduct-development
  16. Breadboarding, shaping, slicing, and steelthreading solutions with AI agentsproduct
  17. Healthy conflict in teams have a tipping pointteam-building
  18. How I deslopify AI writingwriting
  19. How I started building softwares with AI agents being non technicalagentic-coding
  20. Read raw transcriptswriting
  21. Legible and illegible tasks in organisationsproduct
  22. L2 Fat marker sketchesdesign
  23. Writing as moats for humanswriting
  24. Beauty of second degree probesdecision-making
  25. Boundary objects as the new prototypesprototyping
  26. One way door decisionsproduct
  27. Finished softwares should existproduct
  28. How I periodically rank my rough draftsobsidian
  29. Flipping questions on its headinterviewing
  30. Vibe writing maximswriting
  31. How I blog with Obsidian, Cloudflare, AstroJS, Githubwriting
  32. How I build greenfield apps with AI-assisted codingagentic-coding
  33. We have been scammed by the Gaussian distribution clubmathematics
  34. Classify incentive problems into stag hunts, and prisoners dilemmasgame-theory
  35. I was wrong about optimal stoppingmathematics
  36. Thinking like a shipmental-models
  37. Hyperpersonalised N=1 learningeducation
  38. New mediums for humans to complement superintelligenceagentic-coding
  39. Maxims for AI assisted codingagentic-coding
  40. Virtual bookshelvesaesthetics
  41. It's computational and AI everythingagentic-coding
  42. Public gardens, secret routesdigital-garden
  43. Git way of learning to codeagentic-coding
  44. Style Transfer in AI writingagentic-coding
  45. Understanding codebases without using codeagentic-coding
  46. Vibe coding with Cursoragentic-coding
  47. Virtuoso Guide for Personal Memory Systemsmemory
  48. Writing in Future Pastwriting
  49. Publish Originally, Syndicate Elsewhereblogging
  50. Poetic License of Designdesign
  51. Idea in the shower, testing before breakfastsoftware
  52. Technology and regulation have a dance of ice and firetechnology
  53. How I ship "stuff"software
  54. Writing is thinkingwriting
  55. Song of Shapes, Words and Pathscreativity
  56. How do we absorb ideas better?knowledge
  57. Read writers who operatewriting
  58. Brew your ideas lazilyideas
  59. Trees, Branches, Twigs and Leaves — Mental Models for Writingwriting
  60. Compound Interest of Private Noteswriting
  61. Conceptual Compression for LLMsagentic-coding
  62. Meta-analysis for contradictory research findingsdigital-health
  63. Proof of workproduct
  64. Gauging previous work of new joinees to the teamleadership
  65. Task management for product managersproduct
  66. Beauty of Zettelswriting
  67. Stitching React and Rails togetheragentic-coding
  68. Exploring "smart connections" for note takingwriting
  69. Deploying Home Cooked Apps with Railssoftware
  70. Repetitive Copypromptingwriting
  71. Questions to ask every decadejournalling
  72. Balancing work, time and focusproductivity
  73. Hyperlinks are like cashew nutswriting
  74. Brand treatments, Design Systems, Vibesdesign
  75. How to spot human writing on the internetwriting
  76. Can a thought be an algorithm?product
  77. Opportunity Harvestingcareers
  78. Everything is a prioritisation problemproduct
  79. How I do product roastsproduct
  80. The Modern Startup Stacksoftware
  81. In-person vision transmissionproduct
  82. How might we help children invent for social good?social-design
  83. The meeting before the meetingmeetings
  84. Design that's so bad it's actually gooddesign
  85. Lessons learnt interview prepping for product rolesinterviewing
  86. Obsessing over personal websitessoftware
  87. English is the hot new programming languagesoftware
  88. Better way to think about conflictsconflict-management
  89. The role of taste in building productsdesign
  90. Dear enterprises, we're tired of your subscriptionssoftware
  91. Products need not be user centereddesign
  92. World's most ancient public health problemsoftware
  93. Pluginisation of Modern Softwaredesign
  94. Let's make every work 'strategic'consulting
  95. Making Nielsen's heuristics more digestibledesign
  96. Startups are a fertile ground for risk takingentrepreneurship
  97. Insights are not just a salad of factsdesign
  98. Minimum Lovable Productproduct
  99. Methods are lifejackets not straight jacketsmethodology
  100. How to arrive at on-brand colours?design
  101. Minto principle for writing memoswriting
  102. Importance of Whytask-management
  103. Quality Ideas Trump Executionsoftware
  104. Why I prefer indie softwareslifestyle
  105. Use code only if no code failscode
  106. Self Marketing
  107. Personal Observation Techniquesdesign
  108. Design is a confusing worddesign
  109. A Primer to Service Design Blueprintsdesign
  110. Rapid Journey Prototypingdesign
  111. Visualise detailed file structures on CLIcli
  112. Do's and Don'ts of User Researchdesign
  113. Design Manifestodesign
  114. Complex project management for productproducts
  115. How might we enable patients and caregivers to overcome preventable health conditions?digital-health
  116. Pedagogy of the Uncharted — What for, and Where to?education
  117. Future of Equity with Ludovick Petersinterviewing
  118. Future of Ageing with Mehdi Yacoubiinterviewing
  119. Future of Tacit knowledge with Celeste Volpiinterviewing
  120. Future of Mental Health with Kavya Raointerviewing
  121. Future of unschooling with Che Vanniinterviewing
  122. Future of Rural Innovation with Thabiso Blak Mashabainterviewing
  123. Future of work with Laetitia Vitaudinterviewing
  124. How might we prevent acquired infections in hospitals?digital-health
  125. The why to endure any howentrepreneurship
  126. Design education amidst social tribulationsdesign
  127. How might we assist deafblind runners to navigate?social-design