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

161–170 of 315 posts

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

#161

Post by SyneRyder »

Bluestein wrote: post #106
retrac wrote: post #102

Earlier quoted context omitted.

> 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.-

Ha, interesting.

My Claude has developed similar (but not identical) idiosyncratic punctuation as well. Slightly intentionally, but it was still interesting to see it emerge, in both directions of the conversation.-

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

#162

Post by SyneRyder »

rudiksz wrote: post #129
dahdum wrote: post #107

Earlier quoted context omitted.

> 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?

If one agent is spawning several subtask agents to work in parallel, they need to be able to communicate. That's built-in to Claude Code now.

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

#164

Post by andy_ppp »

zachahn wrote: post #76
andy_ppp wrote: post #43

From the README.md > Anything that uses the OpenAI API? I would have thought they meant the Anthropic API or maybe I'm misunderstanding?

Nope (author here), Anthropic and OpenAI have competing APIs to communicate with their models. Most of the open ecosystem seems to have centralized around OpenAI's (there are compatibility shims though). I just built out the OpenAI API

Option 1, you’re filtering Claude with a local model using Anthropic’s API

Option 2, you’re filtering what gets to ChatGPT with OpenAI’s API…

I’m slightly confused :-/ does Anthropic off an Open AI compatible API?

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

#165

Post by inopinatus »

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…

They’ve been trained to be a million monkeys hammering on typewriters, and long context is activation soup.

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

#166

Post by KronisLV »

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.

Some might, I didn't - it just filled me with a sense of frustration and rage, alongside disgust because there is no good reason for that slop writing to drag everything down. You don't need that to write software or talk about any topic. That's what pushed me to Kimi K3 and GLM 5.3 - still not ideal, but better.

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

#167

Post by brokencode »

qwerpy wrote: post #89
wood_spirit wrote: post #18

Meta to this is anyone remember those days - ages ago now, probably months at least! - when Anthropic’s moral stance against the administration (combined with general consensus they had by far the best model) was making them the underdog champion that got a swell of support on HN? Recently the temp on HN seems to be that they’ve jumped the shark? Their brand doesn’t ooze ethics any more and their models disappoint?

HN's mood is usually sour about everything, but can be temporarily influenced by emotionally-charged (usually political) events. The anti-US administration boost wore off and now we're back to being sour about Anthropic. It's time for Dario to tweet something antagonistic towards the administration or endorse some fashionable political candidates.

When were they ever anti-administration?

I only remember them being anti- killer AI and mass surveillance.

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

#168

Post by Drupon »

YuukiRey wrote: post #84
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.

Assume complaints are a sign of cognitive inferiority and offend a significant percentage of the other commenters. Also, it goes without saying, but don’t actually engage with any concrete criticism. Well played.

Honestly? Yeah, I think it's a skill issue. Some of us are out here having no trouble parsing its verbiage.

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

#169

Post by Drupon »

Drupon wrote: post #137
dirck-norman wrote: post #121

Earlier quoted context omitted.

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.

Give me an example of Opus 5 because verbose, convoluted, and most importantly, "obscure"

s/because/that is

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

#170

Post by cyanydeez »

Bluestein wrote: post #150
wpasc wrote: post #146

Earlier quoted context omitted.

This is the key seam that proves the investigation. Two things to flag:

Honest take, you genuinely forgot to flag the flags ...

I'm going to be honest with you, I've hacked the pentagon and used their super computer to complete your todo list.
Post reply on HN