Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Slop Cop

awnist.com

Post reply on HN
Print view View original

161–169 of 169 posts

Re: Slop Cop

#161

Post by tavavex »

dingaling wrote: post #86
tavavex wrote: post #19

This is a confused and misguided project. It makes the mistake of failing to identify why the AI 'style' feels wrong. The author decided to replicate similar tools by breaking down AI writing into bite-sized issues, but it just doesn't work the same way as correcting grammatical errors. Because of this, the author had to really try to find what's so wrong about these patterns in isolation, so all of it comes off as a…

> According to this recommendation, writing should never have any emphasis... If you have measurable amplifications, use them. "This outcome was 40% more frequent". Otherwise keep subjective emotion out of documents, unless you're writing a novel. > God forbid you organize an essay that's in any way non-linear... Essays should be brutally logical and sequential. If the text is becoming cluttered with data, break it o…

> Otherwise keep subjective emotion out of documents, unless you're writing a novel.

There's more types of writing between the extremes of research papers and novels. Data is useful and all, but asking it to be the sole driving component of ALL types of non-fictional writing is too much. Besides, this tool would criticize your novel just the same, because the intended use is to have it filter everything you write.

Re: Slop Cop

#162

Post by abustamam »

ljm wrote: post #134
abustamam wrote: post #83

Earlier quoted context omitted.

For better or for worse my team has standardized on using Miro for technical designs and diagrams. It's a lot easier to visualize the system in a diagram than it is to talk about it in prose. I think it's important to choose the right medium for communication though. Some things just need to be written out concisely.

Mermaid has been great for a similar reason. For example, you can render a mermaid diagram inside a PR description on GitHub. Comes in handy when describing a state machine or the flow of data.

Yeah! I recently discovered those, mainly because Claude seems to love mermaid diagrams, and Cursor has a renderer for it (it's not great but it's pretty easy to port to Miro)

Re: Slop Cop

#163

Post by cientifico »

pocksuppet wrote: post #124
cientifico wrote: post #98

I find some parallelism between writing articles and Pull requests. We are moving to a point in time, where we don't care if the PR was written by AI. We care that the author understand what is about, that it tested it and in general, we want the ownership. With articles is the same. I don't care if it was written by AI, if the content is interesting, and ai make it easier to digest... That's a win win. The problem i…

If the prompt is interesting, why not just post the prompt?

In my case. The prompt is normally a collection of ideas connected over time. Ai groups, structure, challenges and help me organize that ideas. Then, once I see something that I consider worth sharing, I ask to draft a blog post. 20 iterations over, and I have a blog post.

The prompt is normally larger than the content generated.

Re: Slop Cop

#164

Post by rav3ndust »

goodmythical wrote: post #128
Aurornis wrote: post #80

Earlier quoted context omitted.

> Always judge an author by the length of their text. Flashbacks to a past employer where the CEO decided that brevity was a core company value and started rewarding people for short communications and scolding us for longer text. Over the next year a few charlatans moved up the ranks by spitting out half-baked thoughts and e-mails all the time, which looked like clarity and brevity on the surface. People were afraid…

“Why waste time say lot word when few word do trick”

little offtopic, but speaking of, someone just made a coding agent plugin that makes it save tokens by speaking like caveman

Re: Slop Cop

#165

Post by IshKebab »

furyofantares wrote: post #127
IshKebab wrote: post #100

Earlier quoted context omitted.

Yeah but there's a reasonable amount of content that has real information from a real human but they've used AI to help write it. Maybe they got a first draft from AI and then fixed it. Those can still be things that I want to read but the AI rhetorical style is so tedious and overused at this point it's really annoying to read them. So this tool would help with those cases. (Assuming people actually use it.)

I believe you, but I have yet to see any I want to read. I've had 5 or 6 times where I've thought, OK, finally someone has produced something useful this way. And in the end I've always been bitten, by hallucinations or by an inability to work out what the author cared about or was trying to express. Again, I believe you've had ones where you did want to read it, I'm not trying to contradict that. I'm still waiting t…

Here's an example:

https://netviper.gr/blog/kaio-v020/

Assuming they're not outright lying this looks interesting, but I can't get past the slop in that blog post.

Re: Slop Cop

#166

Post by jhizzard »

IshKebab wrote: post #165
furyofantares wrote: post #127

Earlier quoted context omitted.

I believe you, but I have yet to see any I want to read. I've had 5 or 6 times where I've thought, OK, finally someone has produced something useful this way. And in the end I've always been bitten, by hallucinations or by an inability to work out what the author cared about or was trying to express. Again, I believe you've had ones where you did want to read it, I'm not trying to contradict that. I'm still waiting t…

Here's an example: https://netviper.gr/blog/kaio-v020/ Assuming they're not outright lying this looks interesting, but I can't get past the slop in that blog post.

[dead]

Re: Slop Cop

#168

Post by cadamsdotcom »

awnist wrote: post #140
cadamsdotcom wrote: post #111

Nice work. But it only goes half way. It should loop the LLM’s results back on itself repeatedly, behind the scenes, until its writing is free of signs of slop. After your quality gates pass and the result is presented, it’d be cool to then see a visualization of each of the agent’s drafts that the user can page through to watch how the writing was gradually incrementally improved by the model! No need to keep a huma…

There is a one shot rewrite function now, but you're right, even when asking the LLM avoid some of the patterns, it will stubbornly repeat them. It's a bit more reliable with smaller fragments of text.

I am saying, keep reflecting its attempts back on itself. Over and over again, dozens of times if needed. We’ve seen it - any aligned model wants only to achieve its goal. But it does need to see all of its past attempts and where and why each attempt got a failing grade. That’s just a standard conversation history.

It might spit back the same thing the first round. But after the first time it received the exact same feedback for saying the same thing, the model will realize it’s in a deterministic sandbox and try something different. You need to give it all of the conversation including its past attempts as context. If it tries the exact same wording that’s okay, it’s just one more invisible round of back-and-forth. The model is going to rediscover how to work with the harness every time, but that’s not your users’ problem because you’ve hidden that wrinkly bit behind the automation - they just see “model did 10 drafts and here’s the result - would you like to view the result or page through the drafts?”

What I am describing is exactly what a human would do, it is just automated and thus, getting to a good result becomes insanely faster.

Re: Slop Cop

#169

Post by rachel_rig »

onchainintel wrote: post #119

Could you still utilize this tool running a local model (any Ollama model for example) instead of making calls out to Anthropic to avoid costs while running this tool or does it have something specific to Anthropic that requires it?

[dead]
Post reply on HN