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

121–130 of 315 posts

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

#121

Post by dirck-norman »

Drupon wrote: post #68

I'm surprised by this reaction to Claude's verbiage recently. I don't have any issue immediately understanding what it's saying, but then again I read regularly and a lot of the people I know complaining think it's an accomplishment in literacy to get through Dungeon Crawler Carl.

Being verbose, convoluted, and obscure does not make you intelligent nor more literate.

Often it’s exactly the opposite. True intelligence and literacy is being able to communicate effectively and to a broad audience in the simplest terms possible.

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

#122

Post by zachahn »

vardalab wrote: post #66
juancn wrote: post #28

Just set the following incantation: You must use ASD-STE100 Simplified Technical English (STE) when it doesn't detract from meaning.

I actually changed the output style for Claude Code to use ASD-STE100 and it still doesn't help that much. It still comes up with a lot of stupid words like this gem "Standing where it stood"

Yeah I agree... I also tried output styles, tried using hooks to repeatedly tell it to be a little better. I don't think it helped, as I was always frustrated with it.

I found vomit with a small LLM much better than anything Opus 5 ever wrote. I don't think Opus 5 can write.

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

#123

Post by zachahn »

Bluestein wrote: post #6
pebbly_bread wrote: post #4

I think this needs a before and after example

The author's blog has what follows (link also follows): [Seriously y'all in what universe would some "caveat" or another NOT "be a real one" by whatever severity you'd want to measure that AND/OR need of saying so ... ] Claude (Original) Force pushed. 1234567...890abcd main -> main (forced update). Verified Local main and origin/main both at 890abcd, in sync. Every commit reachable from origin/main: no old string fou…

Hehe thanks for sharing the example, and thanks also for posting! Made my day :)

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

#124

Post by qlte »

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…

I believe we are several generations past peak-RLHF at this point. Now it's much more RLVR (Reinforcement Learning with Verifiable Rewards), with a goal/evaluator loop.

Which, conveniently, fits neatly into the benchmaxxing arms race/agentic coding market fit, since you can basically train "directly" on a specific problem space for a benchmark/agentic goal (fudged sufficiently to avoid excess overfitting on public problems/bechmaxxing accusations if real world performance falls short).

The language evolution could be explained by reliance on ever increasing layers of a model judging a model, using a model developed eval, based on synthetic data from a model, etc. And by the time a human evaluator sees it both A/B choices already converged into weird Claude pseudo English as that was baked in much earlier in training.

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

#125

Post by flipthefrog »

Telling Opus 5 or Fable to route answers through Opus 4.6 usually works pretty well. 4.7 really was the version where the writing style became horrible. I also have a Codex subscription in addition to to Claude 20x, that i use mainly for rewrites of Claude doc vonit and explaining Claude's plans

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

#127

Post by rudiksz »

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,…

Claude is the Deepak Chopra of computer programming. Reviewing PR's created by it is 90% digesting the meaningless word salads in the comments, and the rest is figuring out that it has nothing to do with the code it is commenting.

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

#128

Post by porkpieshoe »

cafebeen wrote: post #114
svara wrote: post #81

Earlier quoted context omitted.

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,…

One danger in acclimating to this style of communication style is that we may accidentally use it in your own communication with other people. If the other person hasn't grokked the dialect, it can make things quite confusing (to say the least). For example, there is common jargon used by people and there is chat-session-specific jargon created by LLM agents, and I've seen the latter popping up in various meetings, u…

You're absolutely right, it would be a load-bearing mistake to adopt LLM jargon as a human speaker.

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

#129

Post by rudiksz »

dahdum wrote: post #107
svara wrote: post #81

Earlier quoted context omitted.

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,…

> it's speaking its own dialect, and you get used to it Same experience. It’s not very “human” but once you have agents talking to each other the shared dialect and verbosity makes things much smoother in my experience. Fighting against the default feels like an uphill battle with no meaningful benefit.

"agents talking to each other"? Are you for real dude?

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

#130

Post by 0xffff2 »

retrac wrote: post #102
svara wrote: post #81

Earlier quoted context omitted.

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,…

> Its use of "dense jargon" and "stilted metaphor" is actually surprisingly consistent - it's speaking its own dialect, and you get used to it. This dialect is idiosyncratic to you and Claude based on your session history and memory. I've noticed Claude's output mimics my writing style. > Registers the board implements but whose behaviour is not modelled Right down to my preferred spellings. As several comments I've…

You're just lucky that your preferred spelling happens to align with Claude's. It is categorically impossible to get any Anthropic model to consistently use American spelling in the last few releases.
Post reply on HN