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

101–110 of 315 posts

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

#101

Post by hellohello2 »

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,…

I agree to some extent about the jargon (Claude has a bigger vocabulary that me, if it knows a useful word I don't I'm fine with learning it), but often times the way information is laid out across sentences just doesn't make any reasonable sense. At least its consistent in the ways its atrocious, sure, but like...

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

#102

Post by retrac »

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,…

> 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 read on HN suggest, this jargon which can be so precise in the mind of one person, tends to rapidly fall apart when multiple people try handling it.

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

#103

Post by extr »

incrudible wrote: post #49
extr wrote: post #23

I'm sorry but the whining over LLM output styles is embarrassing. Do Claude and GPT models always respond in exactly the way my most articulate coworker would? No. The overused jargon is absolutely annoying. But these things aren't my drinking buddies, they're professional tools. It's not _literally unreadable_. It's just not ideal. Most of my tooling is "not ideal". That's okay. That's what I'm paid for. I just work…

Opus 5 is literally unbearable to read for me, but more importantly, it is much worse than 4.8 and that one was already annoying. The more they train it on its own output, the more pronounced its idiosyncrasies become.

It's "literally unbearable" when the AI that completes software engineering tasks at 100x speed and quality from 2 years ago uses too much jargon?

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

#104

Post by Bluestein »

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...

"From neuralese to moron-code ..." :)

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

#105

Post by astrange »

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.

Pretraining is full of bad writing and it doesn't really cause issues. Writing style comes from post-training. In this case it's gotten worse because they prioritized agentic abilities.

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

#106

Post by Bluestein »

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…

I concur. It even follows some idiosyncratic punctuation if you have it.-

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

#107

Post by dahdum »

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,…

> 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.

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

#108

Post by Bluestein »

sroussey wrote: post #100
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.

What an honest take.-

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

#110

Post by extr »

bcooke wrote: post #41
extr wrote: post #23

I'm sorry but the whining over LLM output styles is embarrassing. Do Claude and GPT models always respond in exactly the way my most articulate coworker would? No. The overused jargon is absolutely annoying. But these things aren't my drinking buddies, they're professional tools. It's not _literally unreadable_. It's just not ideal. Most of my tooling is "not ideal". That's okay. That's what I'm paid for. I just work…

The “whining” stems from watching the communication style obviously degrade, and it’s a huge problem for people who want to use this stuff to build and instead continually fight the tools. Like so many other products, people are moving too fast and shipping things that move the ground under people’s feet needlessly. All this while we’re beaten to death with the marketing and false promises, and the broader consequenc…

Sounds like you have a lot of axes to grind outside of simply "the latest models regressed on delivering concise prose".
Post reply on HN