Vomit: Clean up Claude 5's token output with a separate LLM • Hacker News Board

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

#91

Post by zachahn » Thu, Aug 20, 2026, 5:56 PM UTC

palmotea wrote: post #58

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…

> The baked in communication style of these models is so obnoxious it's impacting my work. The best way I can describe it is that everything is optimized to impress the user and make the agent sound more authoritative, but the way this is done is through deliberate obfuscation, inserting inappropriate and extremely dense jargon, and bizarre, stilted metaphors. It's like they've been trained to produce output that's h…

Idk, there kinda are. OpenAI's models are pretty nice too. I haven't tried enough of them but there are powerful local models. I don't feel as good paying OpenAI as I do paying Anthropic for some reason... but paying for improved mental health: priceless.

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

#92

Post by headcanon » Thu, Aug 20, 2026, 5:57 PM UTC

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…

That depends on the output's purpose: if the purpose is to produce readable text for a human that is _not_ me, like an article or document, then I care more about clarity, plain-speaking, and general register. If the goal is to accomplish a specific task, I don't care as much about the prose quality: I'll put up with "Honest Framings" and "load-bearing" since it seems to me that's the token that needs to be in the context for it to function.

I've been in the habit of pushing my claude-speak to codex to improve legibility, but only if I think someone is going to read it.

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

#93

Post by floil » Thu, Aug 20, 2026, 5:57 PM UTC

pickledish wrote: post #11

imalerba wrote: post #5

I like the "Claudish to English" name better. https://github.com/gvzdv/claudish-to-english

Word, that one also includes an example which is great, shows really clearly what the issue is for those who might be less familiar

I'm unfamiliar with claudish and the example helped show the problem. But! There was something uncomfortably familiar in the Claudish example -- this is the way human programmers write when they're deep in the weedy details, and writing the changelist description afterwards as if coming up for air. Overuse of parentheses in nested lists especially, as if the English text needs to bend to the strict needs of a C++ parser.

The rewrite did seem to lose the important fact about the ensure- pattern being idempotent.

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

#94

Post by crab_galaxy » Thu, Aug 20, 2026, 5:57 PM UTC

svara wrote: post #81

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'm probably going to be going against the grain here, but I think it's not as bad as it looks at first. I was similarly frustrated a few months ago, but have noticed I've started to learn the idiom. Its use of "dense jargon" and "stilted metaphor" is actually surprisingly consistent - it's speaking its own dialect, and you get used to it. After a while it gets much easier to read and even becomes somewhat efficient,…

“Filters, including no filters. The request carries whatever filter object the page already has.

…

No step here involves choosing based on meaning. It is a filter, a sort, and a slice.”

This is from Opus five minutes ago. I can certainly derive meaning from these kinds of statements in isolation, but paragraph upon paragraph of this is unintelligibly dense when trying to work with Claude to come up with a plan.

The worst part is that it can’t even make its responses make sense when asked to summarize in simple English or < 200 words. It simply cannot be steered to make its prose legible.

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

#95

Post by akersten » Thu, Aug 20, 2026, 5:58 PM UTC

bcooke wrote: post #51

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…

Very well said. And when you say it like that, I have to wonder how much of this is a natural consequence of RHLF on such a grand scale, when you have millions of people pretty much much skimming chat responses or operating outside their depth and giving unqualified feedback to the models. Seems like a lot of people may be reinforcing what sounds smart over what is smart. Also as an aside: funny how much the LLMs con…

> or operating outside their depth and giving unqualified feedback to the models

I wonder if the labs are sufficiently prepared to filter this kind of stuff out. I see a lot of non-developers asking development things of Claude, getting confused when they're in over their depth, and getting upset that they don't understand what the model is providing them, giving it bad feedback, and subsequently making the AI worse for the rest of us who know how to use the tool.

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

#96

Post by misterio7 » Thu, Aug 20, 2026, 6:00 PM UTC

DaSHacka wrote: post #44

johnnyApplePRNG wrote: post #36

Or just take full control of your agentic coding experience with Pi Coding Agent and picking and choosing your favorite model's API discounted on flex pricing on deepinfra.com instead. I highly recommend it. Claude and Codex usage limits cannot be trusted. Paying your own API bills in full is superior.

I use Pi but with my codex subscription, still preferable to paying the API cost (and I know I would be, as I track how much the cost 'should' be via token api pricing). Wish I could use my Claude subscription with pi too, much preferable to the endless command execution allow/deny prompts you have to do with CC, versus proper autonomous allow/deny lists defined ahead of time. Curious why you recommend the API? It's…

You might be interested in pi-claude-bridge, works nicely.

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

#97

Post by zachahn » Thu, Aug 20, 2026, 6:00 PM UTC

nycdotnet wrote: post #45

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…

Unfortunately this may only start to get worse as the AIs are trained on more and more AI generated content.

I'm not super sure if this is true (yet?). I think that these newer LLMs are trained on results (the agent got some code to run with minimal prompting), and not on text. (I think this is called RLVR.)

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

#98

Post by Bluestein » Thu, Aug 20, 2026, 6:06 PM UTC

_zoltan_ wrote: post #57

Bluestein wrote: post #22

Earlier quoted context omitted.

Pre Trump-castration Fable was verbose, but had a point , and used that wordiness to say or show the indeed intelligent things it reasoned about. This, whatever this is, is something else.-

Is the nerfed Fable worse or better than Opus 5?

The problem here is that "better" is load-bearing, and I mean this half-seriously :)

I would opine:

- Nerfed Fable is worse than Fable

- ... and I would argue Opus 5 is worse than nerfed Fable, to the point I've found it unusable.-

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

#99

Post by medwards666 » Thu, Aug 20, 2026, 6:11 PM UTC

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...

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

#100

Post by sroussey » Thu, Aug 20, 2026, 6:12 PM UTC

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…

So many vacuous statements at the seam. This is the hermetic load bearing part, which I confirmed rather than assuming.