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

191–200 of 315 posts

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

#191

Post by artdigital »

throwaway219450 wrote: post #175
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,…

I’m starting to think this is why Opus suddenly started making 4-5 line comment blocks. They justify why a change was made and gives the next agent something to go on. I delete them and move on, but no amount of “don’t over comment” “match comment style” makes it persistent. I am definitely guilty of wondering why past me made such a harebrained decision, and why past me didn’t think to write any notes, but does it m…

I noticed the increase in comments too and it’s really weird.

Or adding notes to docs of what this doc isn’t when I corrected it. Eg I told it “keep the deployment manual and readme separate, they’re not the same thing”, then Claude added “this is the deployment document and not the README. They should be handled as separate documents and are not the same thing” to the deploy doc lol

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

#192

Post by pooploop64 »

Can't wait for tomorrow's HN front page so we can learn about the 5 additional AI tools needed to make this work properly. And then the day after, each of those will require more agentic tools to manage the agents that manage the agents that manage the agents. Then you need to install Flooper to stop Wigwam from too aggressively rebooting the Glupgo instance that's in charge of making sure your credit card information doesn't get leaked by Chingler, which is needed to manage a shared clipboard between some of the agents but not all of them.

It's like a joke. I thought using AI was supposed to be easier than learning real skills, but I shudder to imagine having to rig up a 100 layer clusterfuck of nonsense like what some of you are apparently running. When will it finally be enough for the output to be worth anything? Is there any plan for that or is the plan to just keep throwing more of the exact same shit at the same wall until we're all dead?

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

#194

Post by broodbucket »

happycube wrote: post #155
unshavedyak wrote: post #54

Earlier quoted context omitted.

It's such a great example. It writes so well compared to Claude. I'd love to know what the hell Antrhopic has done to make Claude's writing so, so bad.

What's sad is that, at least in some cases, Sonnet 3.5's writing was actually pretty good. Sometimes even good enough to read outloud verbatim.

The bar for that is sadly low, see https://www.youtube.com/watch?v=wlYa8NV5k-U

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

#195

Post by striking »

8cvor6j844qw_d6 wrote: post #190
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,…

A separate /clear and /code-comment-hygiene works much better than including instructions related to comment verbosity after carrying out a task. Claude somehow is unable to stop writing excessive comments when carrying out a task.

I've added code comment hygiene to a skill that all of my pull requests go through, alongside a review from a separate agent and a settle loop against bots in my GitHub workspace (since output style has seemed to only help literally the output I see from the model).

A maximum of 20% comment lines added to total lines added and pasting in https://devblogs.microsoft.com/oldnewthing/20260812-00/?p=11... has done wonders.

Even as the most Ant-pilled guy out there, I will take a moment to note that Codex on 5.6 models needs none of this...

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

#196

Post by anon373839 »

qlte wrote: post #124
bcooke wrote: post #51

Earlier quoted context omitted.

Very well said. And when you say it like that, I have to wonder how much of this is a natural consequence of RHLF on such a grand scale, when you have millions of people pretty much much skimming chat responses or operating outside their depth and giving unqualified feedback to the models. Seems like a lot of people may be reinforcing what sounds smart over what is smart. Also as an aside: funny how much the LLMs con…

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.

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

#197

Post by latentsea »

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,…

We should push back on this rubbish.

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

#198

Post by latentsea »

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.

It's negatively affecting my mental health too, and I'm considering the same switch for the same reasons.

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

#200

Post by latentsea »

benjismith wrote: post #133

I think this is just another part of the growing pains of working with machine intelligence that we have to endure. Much like we previously had to cope with "hallucinations" as an issue. If the ultimate goal of AI is to develop general intelligence, the first big objective is: thinking systematically. And the road toward systematic thinking right now is mainly coding, mathematics, and other "verifiable reward" domain…

It's slop.
Post reply on HN