Claude Is Always Right

I think I can say, at least for me, why Claude's writing is so freaking awful, even when it's completely correct.

Claude writes technical docs that are true in the same sense that it is true my best friend is a collection of specialized tissues known as "organs" and blah blah blah - and nothing else. Don't ever forget the trailing negation, it is omitted never.

Another take: Claude writes like your best friend describing a great first date. "Ok we were going to meet at 8 - did I mention it was Friday? Right, 8 oclock at the Italian place and no place else. During dinner he accidentally spit out some food, but I thought i was funny! That's because we were laughing so hard after we discovered we were both from Omaha. That was before dinner, during drinks, when we couldn't get rid of Alfred. His place really needs a deep cleaning!"

Perhaps with all of the hope for an LLM-authored movie, we try for something non-linear?

6 points | by KenPainter 17 hours ago

7 comments

  • hxugufjfjf 52 minutes ago
  • talmr 10 hours ago
    I use AI for writing api docs to ensure they’re concise and accurate, factual.

    I write my own messages, like this one, for things where I think my humanity is more important.

    My api docs are consumed by AI agents anyway. Maybe 10% of its readers are humans now.

  • adriant93 13 hours ago
    You can train your Claude to write in your own words if you just feed it enough of your work to understand your tone and patterns. It's not a full fix, but it definitely improves it.

    Also, from my experience ChatGPT is better at writing - and this is coming from a Claude Ultra user btw.

  • abraxas 16 hours ago
    It's likely because LLMs by their nature can't backtrack. It will probably improve the output if you tell it to rewrite the response in a linear flow without digressions.
    • KenPainter 16 hours ago
      Tried that about a year ago. Later came many others, all of which worked more or less well until they didn't.

      After a while I realized I was like a crazed gambler, way down, at the blackjack table whose friends can't drag me away because "I've got a system! I've got a system!" They say, "But you're losing!", "I'm refining the system! I'm refining the system!"

      The closest I came was writing a large amount myself, then putting in AGENTS.md to read certain docs as the "house style". But if you let it write one additional doc, it pulls the house style to mediocrity, and the second makes it worse and so on.

      I've gone black-and-white on prose and code. Code is LLM-author/human-review, prose is human-author/LLM-review.

  • vismit2000 12 hours ago
    You are absolutely right!
  • colesantiago 16 hours ago
    The way Claude writes is atrocious. It is mostly due to the fact that Anthropic isn't prioritising writing skills.

    That may change in the future but for now, bleh.

  • Theophane_Rame 10 hours ago
    [dead]