Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Vomit: Clean up Claude 5's token output with a separate LLM

github.com

Post reply on HN
Print view View original

181–190 of 315 posts

Re: Vomit: Clean up Claude 5's token output with a separate LLM

#181

Post by gabriela_c »

trefoiled wrote: post #31

I've been grappling with this for weeks, not just in Claude but in Codex as well, which isn't quite as bad but still annoying. AGENTS.md does very little, agents will consistently violate the communication preferences, especially as the session drags on. It's incredible to me that there's no good way to reliably change the way an LLM responds to you that a workaround like this would even be necessary. It seems like s…

What are you talking about? Every major agent allows hooks, Claude has exceptional hook support

Re: Vomit: Clean up Claude 5's token output with a separate LLM

#182

Post by jesse_ash »

ericpauley wrote: post #42

I suspect that sustained reading of Opus 5's unconscionably bad prose could actually cause psychological harm. We're strongly considering moving all of our Anthropic spend to Codex/open weight models. It's a mental health decision at this point.

Personally, I had to go back to Opus 4.6 after I felt what I thought were some early onset signs of psychosis.

It seems ridiculous to type, that a model could have this effect on my mental health, but my quality of life and enjoyment of work has improved drastically since I stopped subjecting myself to reading this style of output 8 hours a day.

Re: Vomit: Clean up Claude 5's token output with a separate LLM

#183

Post by andai »

trefoiled wrote: post #31

I've been grappling with this for weeks, not just in Claude but in Codex as well, which isn't quite as bad but still annoying. AGENTS.md does very little, agents will consistently violate the communication preferences, especially as the session drags on. It's incredible to me that there's no good way to reliably change the way an LLM responds to you that a workaround like this would even be necessary. It seems like s…

I noticed with with OpenAI's reasoning models (o3, o4-mini), and early GPT-5 (but they fixed it there, at least in chat). It went from the 4o "over-familiar" sycophancy to sounding like an absolute robot.

I think it's because the reasoning stream shapes the style of the final output, and they optimized it for density, token efficiency. So it prefers to use more complex language, as a function of the rewards it was given?

Not 100% sure about this argument though (reasoning style -> final response style); Gemini Pro, back when reasoning tokens were public, was different, which was interesting -- it would have a very structured reasoning section, and then the final output was in a completely different style. (I strongly preferred the reasoning section because it was logical and easy to parse! And was very sad when they hid it...)

Re: Vomit: Clean up Claude 5's token output with a separate LLM

#186

Post by andai »

bob1029 wrote: post #20

At some point one has to wonder if it's still worth using anthropic's models if we need to babysit 100% of its output with another vendor's model. Why not just use that other vendor's model for everything? I can't help but feel the circumstances that enable this kind of front page article are vestigial from the days when OAI was super bad and Anthropic was beyond reproach. This change-over-time is why I avoid getting…

So here's the workflow I gathered, from the comments I've read here recently:

- Claude as main agent, but use this skill[0] to make Claude delegate everything to Codex, because it's cheaper and faster. (Hilariously, the skill is official!)

- Use TFA or Claudish to English[1] so the final output is actually human readable.

Ironically it wasn't so long ago that I was asking Claude to rewrite output from other LLMs to make it more readable...

[0] - https://github.com/openai/codex-plugin-cc

[1] - https://github.com/gvzdv/claudish-to-english

Re: Vomit: Clean up Claude 5's token output with a separate LLM

#187

Post by insane_dreamer »

data-ottawa wrote: post #176
insane_dreamer wrote: post #135

Earlier quoted context omitted.

that is not my experience at all; I never write the way Claude does or use its vocabulary. I also find myself regularly editing its code comments, which do not match my expectations of succinct, clear, not over explained, etc. I ask it to read my edited comments to improve its writing, which has helped _somewhat_. (The code itself that it writes is decent, though it still overcomplicates things. I find myself writing…

The only solution I’ve found that works is asking Mistral medium to rewrite all of Claude’s documentation and comments, then I review and rewrite the final draft for anything mistral misunderstood. I find Claude has become very difficult to work with and incapable of writing clear documentation, even when directly prompted or provided samples. As for code, I think each function requires 3-4 passes with Fable to actua…

> The other Claudism that drives me crazy is when it writes comments and commit messages that track how you arrived at an decision instead of what it is.

yes, this is part of what I'm continuously removing from its comments; I've told it multiple times "that belongs in a ticket, not in the code" but to little avail :/

Re: Vomit: Clean up Claude 5's token output with a separate LLM

#188

Post by zmmmmm »

medwards666 wrote: post #99
trefoiled wrote: post #31

I've been grappling with this for weeks, not just in Claude but in Codex as well, which isn't quite as bad but still annoying. AGENTS.md does very little, agents will consistently violate the communication preferences, especially as the session drags on. It's incredible to me that there's no good way to reliably change the way an LLM responds to you that a workaround like this would even be necessary. It seems like s…

This morning I asked Claude to provide a summary of the work it had done but to '... explain it as if you were talking to a moron' and it actually turned out a quite comprehensible summary. So going to continue trying that as a command structure going forwards...

but what if I really am a moron? how do I get that level of explanation now!

Re: Vomit: Clean up Claude 5's token output with a separate LLM

#189

Post by nl »

There's a theory going around on Twitter which goes something like this:

Internal Anthropic employees have been using Mythos since February to orchestrate their (Opus) sub-agents. This works well, and subsequent RL runs have used internal data to improve this. That RL has optimized Opus for agent-to-agent communication which is why you see the bizarre word choices and huge self-justification sections.

I think this theory makes sense. Clearly there is something odd going on, and also if you have ever used Fable to run Opus sub-agents it is almost miraculously good.

Hopefully they'll fix their RL for Opus 5.1

Re: Vomit: Clean up Claude 5's token output with a separate LLM

#190

Post by 8cvor6j844qw_d6 »

striking wrote: post #148
trefoiled wrote: post #31

I've been grappling with this for weeks, not just in Claude but in Codex as well, which isn't quite as bad but still annoying. AGENTS.md does very little, agents will consistently violate the communication preferences, especially as the session drags on. It's incredible to me that there's no good way to reliably change the way an LLM responds to you that a workaround like this would even be necessary. It seems like s…

I asked Claude to do the following: > hello i would like to configure a new output style for you. it should keep the coding instructions (as you will still be coding!) and otherwise produce the same output, but with two new caveats. first, long detailed replies are still permitted, but if employed they must end in a bullet pointed summary whose points are all brief; if the summary attempt ends up not being so brief,…

A separate /clear and /code-comment-hygiene works much better than including instructions related to comment verbosity after carrying out a task.

Claude somehow is unable to stop writing excessive comments when carrying out a task.

Post reply on HN