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.
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.
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.
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"
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.
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.
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.
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.
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.
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.
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?
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.
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.
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.
You know the problem; then why not address it? Does Compacting the context not help?
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.
I haven't had the same problems others have but I'm also not a heavy user of it.
I did not see an explanation though.
"Vomit: Clean up Claude 5's token output with a separate LLM" (github.com/zachahn)
285 points | 23 hours ago | 288 comments
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.
https://github.com/backnotprop/bro/blob/main/skills/bro/SKIL...
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.
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.
why do you choose gemini? imo this is a fundamental problem of all frontier ai models.
Haven't tried, because I have just been using 4.6 since 5 was released.