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

111–120 of 315 posts

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

#111

Post by omsta »

Drupon wrote: post #83
tills13 wrote: post #73

Earlier quoted context omitted.

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 ave…

If you really must have a counterexample, though I am afraid it will not reach you given your apparent stance about the other people, when I read Shakespeare I am constantly thinking of poetic ways to translate sentences and paragraphs into my native language (which, for the record, I consider to be great fun), yet Claude has been delivering the gibberish with increasing velocity, yes, even to me.

That said, I must confess that I have not been complaining per se—I assumed that Claude was getting better and better at mimicking the idiosyncrasies of Silicon Valley bro-speak. Judging from other comments, this may not seem to be the case after all.

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

#112

Post by Avshalom »

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…

Jesus

Yes. agents.md does very little because prompts change the context and thus the initial path into/though but they don't/can't change the actual weights that control responses. Yes. of course it gets worse as the session goes on, assuming the prompt is even still in the context window, the further it gets away from it the less it affects next token selection.

This shit is only like 5 years old why can't anyone remember how it works

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

#113

Post by cjk »

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...

After a huge wall-of-text response, I regularly ask Claude to "explain like I'm five, using succinct bullet points," and it works remarkably well.

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

#114

Post by cafebeen »

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,…

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, unbeknownst to the speaker. Some people call it out, but others may simply disconnect from the discussion.

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

#115

Post by jerkstate »

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,…

the only thing that still kind of annoys me is constantly being told what something is not, but even that statement is load-bearing (see what I did there) because it records how it ended up with this decision, because it's not that other choice that it mentions.

FWIW, I also think the constant chorus about how new models are worse than old models is a human hallucination. They're certainly not perfect but every one becomes more steerable in terms of actually completing more and more complex work.

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

#117

Post by zachahn »

Der_Einzige wrote: post #63
aenis wrote: post #9

Earlier quoted context omitted.

Intentionally deferred.

That means it doesn't work.

I have a transcript on my blog post. Someone copied the transcript here too, search "spice‑harvester" on this page (I asked it to replace some of my personal project names with words from the Dune universe).

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

#118

Post by cjk »

mechazawa wrote: post #55
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'll give that a try. Hopefully it reduces the text vomit Claude tends to do. Right now all I have is > - Give terse and concise answers unless the user asks you to elaborate. Big walls of text are not usefull when trying to communicate.

I recently asked Claude (Opus 5) to give me guidance on how to instruct it to be less verbose in a way that it will _actually follow_. Its response was something to the effect of (and I'm heavily paraphrasing here) "'Succinct' and 'short' aren't objective measurements. Try providing a strict word budget instead."

Given that guidance, I tried specifying "Unless I ask you to elaborate, respond with no more than one paragraph, using sentences of 20 words or fewer." It works...ish. I still see it violate this rule regularly, but it's less bad IME.

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

#119

Post by aidanhs »

Drupon wrote: post #83
tills13 wrote: post #73

Earlier quoted context omitted.

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 ave…

Every single time Claude has confused me and I've asked what it's talking about, it's because it's got something completely wrong and has managed to obfuscate the wrongness behind never-introduced terminology, poor analogies and (what I can only assume is) exposure to wording it's used in its chain of thought reasoning.

A single question is enough for it to retract the error and correct itself. Suggesting that not understanding some of these messages is a lack of human comprehension rather than the agent being flat out wrong is...a bold take.

Typically a feature of good human technical communication is the ability to concisely explain key ideas so one can quickly identify any divergences between understanding. Opus 5 is dreadful at this.

The single saving grace is the intuition that if I don't understand it's probably wrong.

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

#120

Post by zachahn »

rootusrootus wrote: post #13

Which Claude 5? Opus 5 does seem to have diarrhea of the mouth. But Fable 5 hasn't been so bad for me. Or perhaps it is just better at adhering to my guidelines.

Opus 5 (author here). My toilet seat is plastic though, I only used Fable while it was available on the $20 plan! That's fair though, it was relatively fine when I did use it, perhaps I should specify.
Post reply on HN