Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

  • Hacker News
  • Don’t use AI to write and don’t use it to edit either. LLMs can’t understand your writing, so the edits and questions about your work will be less helpful than asking another person with knowledge to review.
  • I'm the author of the article.

    There are a number of comments that indicate that I'm using coding agents, and wonder if coding doesn't require the same behavior as writing.

    Coding agents are absolutely a useful tool - however, that doesn't mean that pure "Vibe Coding" is the best approach for most scenarios. Using coding agents correctly requires a careful approach as well, which also starts with thinking through the problem you're solving! The details of workflows for coding and writing are different (in my opinion), but at a high level the same concept applies; don't let an AI do the important thinking for you!

    I'll probably follow up with another blog post with what I've seen work well for coding.

  • While I do agree with the premise of the article, if find this way of thinking applicable for writing code as well. Your code is meant to not only be read by machines, but also other fellow humans. Writing code requires substantial amount of thinking as well. Shouldn't we write code without AI as well?
  • I use it to write in German, because my German sucks.

    I first write the thing myself, then feed it through Deepl Write to see how the AI would write it. It's been very helpful.

    I write everything else myself. However I don't know how I feel about spending my time on Earth typing personal responses to AI-generated messages. Do those people deserve my time and energy?

  • Just this morning I used Claude to build an "omit needless words" app, which lets me paste in text and then marks up that text with strikes through the words that I can leave out.

    I used it to edit a document I'm working on, where I accepted about a third of its suggestions. I feel pretty good about it.

    If you have a Claude account you should be able to access the artifact I built here: https://claude.ai/artifact/RK7XfnaoxVV1Uji84ETaLr - it uses "Claudeception" - the feature of Claude artifacts that lets them use Claude prompts - so it will be billed against your Claude account (at a cost of probably a fraction of a cent per run.)

  • > Writing requires thinking, don't let an AI do the thinking for you.

    Okay, but reading also requires substantial thinking. Moreover, we can say the same about, say, coding. And I am sure there are people who will say, yes, don't use AI to code. But I do, and the results are amazing, and I still think very deeply: in fact, I spend more time with AI coding (and thinking) than before as I do not get hamstrung on, how do I convert this Word doc to PDF in code again? I spend more time in higher order thinking. Same with when I read text written by an AI. I don't believe that writing is any more sacrosanct that coding. And reading and adjusting AI output requires substantial thinking.

  • Once upon a time the word processor was invented, and it made it so much easier to arrange your words on paper. iIf bits were wrong, you could just delete them, or copy and paste them across pages. It was actually pretty amazing what you could do; especially if you didn't mind dot-matrix type on fan-fold paper. Of course if you wanted to make a better impression, you'd type it on a typewriter, or better yet, hand-calligraph your writing with a fountain pen.

    So LLMs allow you to work at the speed of reading, if not faster. So you can try a paragraph here, completely rewrite the tone. Start a chapter in 1PP and just have it rewritten to 3PP. And sofort and so on. The number of new transformations you can do is endless.

    What do a lot of people do? Write a one line prompt and show everyone the oneshot result.

    Ok fine, sometimes you don't need to write amazing prose. But you can also be like the early writers who adopted the word processor. If you put the same amount of elbow-grease into using an LLM as you did writing before, you can get some pretty cool results.

  • So let me get this straight:

    - You can use AI to look through docs and do research.

    - You can use AI to structure your argument.

    - You can NOT use AI to actually write the prose.

    - You can use AI to proofread, especially for how effectively you've communicated.

    I don't know, man, that sounds a lot like using AI to write. Your writing probably says "load-bearing" less than Claude's outputs, but I'm not sure it's much less AI.

Explore Birbla archives