16 comments

  • mmastrac 16 minutes ago
    I've started giving these instructions and I think I've been much more successful in generating clear output:

    Comment blocks are <= 7 words, function names <= 4 words. User-facing message strings should be <= 10 words. Use an active voice, no stage performances, and pick the most common word when choosing among alternatives.

    Limiting the number of words is the strongest factor in cleaning up the output, IMO.

    For older code I've instructed it to delete all the comments, and then I re-comment it using a new session and these guidelines, asking it to rejustify the need for every comment to itself.

    • vrosas 12 minutes ago
      The problem is, when the context window grows, Claude tends to forget these kinds of rules. It will then do whatever it wants. I had to outright ban comments in the global claude.md, the local claude.md AND write a hook to catch any that still slipped through.
      • mandeepj 3 minutes ago
        > The problem is, when the context window grows,

        You know the problem; then why not address it? Does Compacting the context not help?

        • troupo 1 minute ago
          Compacting context compacts context. So Claude forgets a lot during compaction.
  • dataviz1000 0 minutes ago
    > For humans output writing at a 10th grade reading level.

    I put it at the top of CLAUDE.md. I wonder if I put at a 8th grade level, it would be less of a cognitive load.

  • datakan 20 minutes ago
    Has Anthropic said anything about how or why Claude writes the way it does? So many people hate it, seems like they need to do some damage control there.

    I haven't had the same problems others have but I'm also not a heavy user of it.

    • user43928 0 minutes ago
      They added a config option to Claude Code to make the output concise, and promised more comprehensive improvements.

      I did not see an explanation though.

    • the_sleaze_ 7 minutes ago
      They say you aren't interacting with an LLM or a model, but the character that the LLM is playing - the "always be positive and helpful software engineer"
    • chinathrow 15 minutes ago
      The brevity how it outputs words seems like they try to save on tokens delivered.
  • WalterGR 33 minutes ago
    Related and recent: https://news.ycombinator.com/item?id=49375996

    "Vomit: Clean up Claude 5's token output with a separate LLM" (github.com/zachahn)

    285 points | 23 hours ago | 288 comments

  • joduplessis 6 minutes ago
    Just stop using Claude. There are so many other better models right now.
  • walthamstow 30 minutes ago
    It's such a sad indictment of Anthropic's product that so many people hate interacting with it. Claude is on its way to the Microsoft Teams zone of hatred.
    • jayers 4 minutes ago
      I think it would happen with any persona that Anthropic chose. I enjoyed the bouncy, optimistic style at first. I've since grown to hate it.
      • dominotw 2 minutes ago
        how do they infuse this personality? do they train the human feedback providers with a certain personality?
    • matheusmoreira 16 minutes ago
      It's pretty sad indeed. Switching to other models made me notice how weird and verbose Claude was.

      The moralizing is incredibly obnoxious as well. It doesn't seem so bad at first, but it instantly becomes intolerable the second I remember I'm paying for those tokens.

    • esafak 1 minute ago
      They should run a focus group!! https://www.youtube.com/watch?v=C08WmKiwcSs
  • pmarreck 28 minutes ago
    Why couldn't this just be a skill that Claude and Codex could work with instead of something that has to go through Gemini, again?
  • Nevin1901 20 minutes ago
    Fix: Just switch to OpenAI, Grok, or other LLM's. They provide better performance and respond with 5 sentences. They also don't lecture you when you get angry.
    • pkulak 19 minutes ago
      You… get angry?
      • matheusmoreira 15 minutes ago
        Claude will end the conversation if you berate it when it screws something up.
        • lunchbucket 4 minutes ago
          That's interesting but raised the same question, why berate a machine? Either the agent is not a person, in which case, anything it does wrong is your fault. Or it is a person, it can be blamed for mistakes, but then we can't in good conscious use it as a tool.
          • sweetjuly 0 minutes ago
            One must imagine punching the wall feels good (in the moment)
        • Razengan 3 minutes ago
          wow

          I've been saying this since probably a year, that the entire Claude product: from the sign-up, the payment, the UX, the UI, the harness, the intelligence itself, the output, the "flavor" ..is just so _mid_ that all the hype posted on HN about Claude _must_ have been paid PR or a case of the emperor with no clothes.

  • ljoshua 18 minutes ago
    Upvoting if for nothing else than the intro paragraph to the repo. That was hilarious and so true.
  • markatkinson 21 minutes ago
    Oh my gosh it drove me so nuts I switched to GLM5.3, and it was a breath of fresh air.
  • zengid 27 minutes ago
    this isn't just necessary, it's mandatory. that's the difference.
    • collingreen 6 minutes ago
      This is the load bearing comment, and it cuts more deeply than you thought.

      Let me ground my answer so I'm not just guessing. The blast radius of this change is significant and requires careful surgery to get right.

      It's clear now and there's two options going forward: A. Use this tool OP suggested B. Rewrite the Internet from the ground up without this clear contradiction in place - 3-5 days

      I recommend B and started 3 subagents to read all the code before I get started. I'll wait for them to finish.

  • mcv 37 minutes ago
    I wish I didn't need it, but the way Claude talks can get pretty tiresome. I've often wondered why it talks like that. Was it really trained on Buzzfeed? Is Gemini really that much better?
  • lqcfcjx 23 minutes ago
    i hate claude writing a lot, especially after opus 4.8 and it's even worse in 5. in many cases, it feels like playing whac-a-mole and you just can't get rid of all those obvious ai writing patterns.

    why do you choose gemini? imo this is a fundamental problem of all frontier ai models.

  • fowkswe 16 minutes ago
    https://x.com/ClaudeDevs/status/2090245922685063634

    Haven't tried, because I have just been using 4.6 since 5 was released.

    • walthamstow 12 minutes ago
      Concise mode is likely the same buzzword salad but with fewer connecting words and terser sentences. Same with Caveman. The way it writes is fundamental to how it was trained.
      • sscaryterry 4 minutes ago
        Yep, they're putting lipstick on the pig.
  • hmokiguess 6 minutes ago
    [dead]
  • pkulak 20 minutes ago
    [dead]