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

81–90 of 315 posts

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

#81

Post by svara »

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 think, since the odd metaphors it uses often have a precise meaning in Opus-ese (Fable speaks a really similar dialect).

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

#82

Post by rafram »

imalerba wrote: post #5

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

The funniest part is that that project's own readme includes lots of good Claudish.

> If CLAUDISH_MODEL names a model you have not pulled, every rewrite is skipped — with the one-time notice above.

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

#83

Post by Drupon »

tills13 wrote: post #73
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.

It's not that we can't understand what it's saying (for the most part) it's just when something is very jargon-dense, our brains have to pause or take an additional step to deobfuscate the actual meaning of the word or phrase. It's mentally draining.

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 average Claude user complaining about this reads a single novel (that's not sci-fi/fantasy written for teenagers) a year.

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

#84

Post by YuukiRey »

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.

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

#85

Post by throwaway314155 »

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?

I'd expect this to cycle between companies ~monthly until they all IPO. As it turns out people do sometimes prefer speed and better UX. If the model (Sol, for now) has fewer parameters and also happens to be capable of solving deeply complex Fable-adjacent problems sometimes, even better.

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

#86

Post by discreteevent »

mannanj wrote: post #46
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…

That sounds kind of like deception, and a dark pattern not too unlike abuse to me. Though you know, it's not like the leadership tied to these companies have a history of abuse, deception and theft or anything like that, right? It's not like our leaders hide behind similar sorts of patterns that the agents/AIs follow (not saying it's not a human thing - but I hold leadership to higher standards than non-leaders). If…

Yes, AI is a perfect accompaniment to a post-truth world. I'm hoping there will be a backlash soon and that those politicians, tech CEOs and AI will be rudely ousted from their perch and shunned thereafter.

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

#87

Post by zachahn »

pcbro141 wrote: post #61
bcrosby95 wrote: post #39

Earlier quoted context omitted.

> especially as the session drags on. This is because these harnesses are missing a very important feature. Anything like this needs to be included with every turn, otherwise the LLM quickly drifts. I first noticed it when I wrote a harness for D&D (because it's so damn noticeable there), but now I include this for any harness I write.

https://code.claude.com/docs/en/hooks https://learn.chatgpt.com/docs/hooks

I totally agree that hooks help to shovel our instructions through to Claude, but it's so dumb we have to waste tons of tokens (repeated verbatim, over and over) (that we pay for), just to have it ignore the instructions anyway.

I wrote a little bit about it on my blog post. It's a waste of money and compute.

https://zachahn.com/posts/1787191554

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

#88

Post by stronglikedan »

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,…

> you get used to it

And once everyone gets used to it, we'll chide people for writing things themselves, like we're chiding them for writing with AI now, and the ouroboros of life will continue.

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

#89

Post by qwerpy »

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.

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

#90

Post by mbesto »

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…

> AGENTS.md does very little, agents will consistently violate the communication preferences, especially as the session drags on.

Non-determinism at its finest.

Post reply on HN