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

201–210 of 315 posts

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

#201

Post by Tohsig »

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…

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 your strongest opinions and beliefs.

Now, I'll grant that those concepts weren't common outside of techy circles. Just clarifying that the LLMs are amplifying them, not synthesizing.

https://en.wikipedia.org/wiki/Grok

https://wiki.c2.com/?ChadwickBoggs

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

#202

Post by latentsea »

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…

Gross take.

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

#203

Post by latentsea »

extr wrote: post #103
incrudible wrote: post #49

Earlier quoted context omitted.

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?

Nothing is getting completed at 100x the speed and quality.

We have to sit and read these LLM outputs 8 hours a day. The UX of reading the outputs matters a lot.

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

#204

Post by cnity »

striking wrote: post #148
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 asked Claude to do the following: > hello i would like to configure a new output style for you. it should keep the coding instructions (as you will still be coding!) and otherwise produce the same output, but with two new caveats. first, long detailed replies are still permitted, but if employed they must end in a bullet pointed summary whose points are all brief; if the summary attempt ends up not being so brief,…

I've noticed that most people seem to consider the core problem of Claude's output as "too verbose" but I don't think this actually cuts to the heart of the matter at all. It's almost, in some weird way, the opposite: like the text is far too _dense_. It tries too hard to invent odd terminology to try to condense stuff, but it doesn't tell you up front that it is going to call your company wide error-handling mechanism a "flare" (or some other such strange term).

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

#205

Post by digital_ghoul »

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 not sure if this will work for you (with Claude), but I was trying to get luna to get a handle on verbosity and the only thing that worked was setting a strict I also have no idea how useful a system prompt instruction like this will be for codex.

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

#206

Post by dcolkitt »

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,…

Yeah, I think what helps is I just have a running conversation on the Claude app open where I said:

> "I frequently use Claude Code and often find the phrasing and language to be hard to understand. I've noticed it's largely broken down into frequently used 'Claude-isms'. I'd like to use this conversation as a running log to ask you about these phrases when I see them. Understandably you don't have the context of the Claude Code session itself, but that's okay because this is largely about understanding the most common and widely use Claude-isms."

And then I just copy and paste small except and ask about things like "smoke" or "load-bearing" or "tripwire". The responses are surprisingly clearly and plainly explained.

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

#207

Post by ahartmetz »

anon373839 wrote: post #196
qlte wrote: post #124

Earlier quoted context omitted.

I believe we are several generations past peak-RLHF at this point. Now it's much more RLVR (Reinforcement Learning with Verifiable Rewards), with a goal/evaluator loop. Which, conveniently, fits neatly into the benchmaxxing arms race/agentic coding market fit, since you can basically train "directly" on a specific problem space for a benchmark/agentic goal (fudged sufficiently to avoid excess overfitting on public pr…

This, 100%. I don’t think the industry knows how to scale LLMs’ general intelligence much further. The training paradigm is about maximizing very specific behaviors / very specific tasks, but doing lots and lots of them. Which can create the illusion of general intelligence if your tasks are similar to the ones the models were fitted for.

If you have watched The Substance, the transformation feels a bit like when things start falling apart in that one.

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

#208

Post by throwaway894345 »

cnity wrote: post #204
striking wrote: post #148

Earlier quoted context omitted.

I asked Claude to do the following: > hello i would like to configure a new output style for you. it should keep the coding instructions (as you will still be coding!) and otherwise produce the same output, but with two new caveats. first, long detailed replies are still permitted, but if employed they must end in a bullet pointed summary whose points are all brief; if the summary attempt ends up not being so brief,…

I've noticed that most people seem to consider the core problem of Claude's output as "too verbose" but I don't think this actually cuts to the heart of the matter at all. It's almost, in some weird way, the opposite: like the text is far too _dense_. It tries too hard to invent odd terminology to try to condense stuff, but it doesn't tell you up front that it is going to call your company wide error-handling mechani…

Kind of both. On the one hand, it is “verbose” in the sense that it will tell me every little nit that it can think of while doing a task, it will tell me a narrative about its thought process, and it will tell me every other detail it can think of. But it does so in a way that tries to be incredibly dense to the point that I have to struggle to figure out what it is saying. I wonder if there are any “legibility benchmarks” that one could use to determine what prompts work best?

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

#209

Post by throwaway894345 »

jchook wrote: post #174
striking wrote: post #148

Earlier quoted context omitted.

I asked Claude to do the following: > hello i would like to configure a new output style for you. it should keep the coding instructions (as you will still be coding!) and otherwise produce the same output, but with two new caveats. first, long detailed replies are still permitted, but if employed they must end in a bullet pointed summary whose points are all brief; if the summary attempt ends up not being so brief,…

Claude already does summaries at the end of long output but they often sound even more like terse jargon nonsense than the long form, eg “the hardwired seam and the relocated barrel”. Sometimes the summaries feel totally alien to the task or code.

Yeah, or they will make some reference to “the seam” or “it” or something else that assumes you read and followed the prior 3 pages of output.

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

#210

Post by burnto »

Der_Einzige wrote: post #60
ericpauley wrote: post #42

I suspect that sustained reading of Opus 5's unconscionably bad prose could actually cause psychological harm. We're strongly considering moving all of our Anthropic spend to Codex/open weight models. It's a mental health decision at this point.

I've been trying to figure out ways to get models to create actual cognitohazards or memetichazards SCP style. Hasn't worked yet outside of the classic "you're now manually breathing" kind of stuff.

Please keep researching and report back!
Post reply on HN