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

221–230 of 315 posts

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

#221

Post by astrange »

andai wrote: post #183
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 gi…

5.6 has a totally different style again, kind of relaxed and neutral with some definite jokes.

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

#222

Post by Drupon »

latentsea wrote: post #202
Drupon wrote: post #83

Earlier quoted context omitted.

I guess my point is that when people are regularly reading dense and challenging material, they can absorb information quickly. It's a literacy gap. Nothing about Claude's output should slow anyone down who did the readings in their upper and higher education coursework, particularly if they continue to read to keep their mind sharp. Based on the examples of "inscrutable" text I've seen, I would be shocked if the ave…

Gross take.

What about that made you upset

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

#223

Post by ineedasername »

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…

I may have to apologize, quite a bit, for what might only be a small part or perhaps an outsized influence if weighted highly (I can’t be sure, could have been mv dev/null’ed)… well, it’s this— my own style of not-kept-in-check by the need to be comprehensible (legible in Claude-speak) to others is, I’m afraid, to rather allow prose to sprawl and go everywhere and even sometimes nowhere at all until it just drifts off and sort of wakes itself up snoring in the weeds of an unintended topic.

Ruthless pruning is unneeded with an LLM and it can take me twice the time to say half as many words.

And, early in the ‘GPT era, I hadn’t unchecked the “allow your chats to be used in future training etc” box, and definitionally they are longer and denser than others’ prompts in such raw scrapings of training materials…

Sorry.

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

#224

Post by medwards666 »

zmmmmm wrote: post #188
medwards666 wrote: post #99

Earlier quoted context omitted.

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!

Turn on caveman mode first?

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

#226

Post by Terr_ »

tadfisher wrote: post #145
rudiksz wrote: post #127

Earlier quoted context omitted.

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.

Because it is somehow incapable of separating the conversation with its human operator from the code it is generating and commenting on. Incidentally, this is also why prompt-injection works. No one wants to know about the three other approaches tried when reading the first sentence of a function's documentation. No one cares that the implementation was planned in six phases and "Phase 3" will implement this interfac…

> No one wants to know about the three other approaches tried when reading the first sentence of a function's documentation.

Worse: Possibly the three other approaches that weren't actually tried--but are the kinds that someone could easily have put in a similar comment for some similar code.

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

#227

Post by customguy »

theGeatZhopa wrote: post #141
porkpieshoe wrote: post #128

Earlier quoted context omitted.

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

honestly, it's really load bearing and boiling the ocean which we don't want. There is no edge! To avoid speaking vibe'ish I start to speak in 3 words sentences. Like this typical dialogue How are you? that's not/very good. I think too. ... Even complexity works. everything is expressible! Just try it. /S

All is sayable? With three words? That seems unlikely. At least, annoying.

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

#228

Post by 4d66ba06 »

Escapade5160 wrote: post #225

GPT-5.6 models in codex are great at not writing like this. Cheaper, huge usage limits, readable output, and quality code. It's the better system now.

I couldn’t believe how much better GPT-5.6 was when I switched over yesterday!

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

#229

Post by cafebeen »

SyneRyder wrote: post #159
cafebeen wrote: post #114

Earlier quoted context omitted.

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…

I mostly agree. Though sometimes the models come up with useful concepts that I'm happy to be introduced to, like the "shape" of a problem (probably like intelligence being "spiky", and Kiki & Boba). I still don't quite 'grok' what the 'seams' concept is yet though. But I have noticed that while "loosely held" is a convenient shorthand for uncertainty, I don't like that one slipping in to my daily language. Except ma…

For sure, I find many of the LLM-isms to be useful writing techniques and terms (although there's something uncanny-valley about the repetition and density of them).

But what I was more thinking about are truly unique jargon terms / phrases that get generated when deep in a problem. As an example of both of such a term and the phenomenon itself, Claude calls this "fluent compound coinage." They usually make sense in the original context, but get confusing when thrown around otherwise.

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

#230

Post by SyneRyder »

Tohsig wrote: post #201
SyneRyder wrote: post #159

Earlier quoted context omitted.

I mostly agree. Though sometimes the models come up with useful concepts that I'm happy to be introduced to, like the "shape" of a problem (probably like intelligence being "spiky", and Kiki & Boba). I still don't quite 'grok' what the 'seams' concept is yet though. But I have noticed that while "loosely held" is a convenient shorthand for uncertainty, I don't like that one slipping in to my daily language. Except ma…

I suspect you're right that those concepts are now more widespread because of LLMs, but they didn't originate with LLMs. The word "Grok" came from Heinlein in the 60s and using it as "to understand" goes back to at least the 80s. Talking about the "shape of a problem" goes back decades. Ditto for "loosely held", though it's not about uncertainty; it's about being open to ideas and/or evidence that may conflict with y…

Good point, and I probably shouldn't have put grok in quotes there, because I was using it in the Heinlein usage long before Musk hijacked it.

It's interesting then that LLMs are making these pre-existing ideas seem alien in the way they amplify them. I guess I must have known about "shape of a problem" and "loosely held" before Claude, but something about the way I'm using & absorbing those concepts from AI interaction feels weird & memetic. I'm saying that as someone who is pro-AI.

Definitely a good response. Thanks for replying!

Post reply on HN