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

111–120 of 169 posts

Re: Slop Cop

#111

Post by cadamsdotcom »

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 human in the writing-improvement loop. Just show it when it’s slop free.

Re: Slop Cop

#112

Post by Epholys »

When I copy/paste some text I wrote online, even short, it's full of alerts. Maybe I write exactly like a LLM in English? It's not my native tongue, maybe that's why.

Otherwise, almost nothing. I don't know if it's because it's specialized on English or if learning it as a second language makes it really unnatural?

Re: Slop Cop

#113

Post by mrob »

zjp wrote: post #104

This is the Hemingway Editor by another name, and I have the same complaint about it that I have about the Hemingway Editor. See: https://zjpea.substack.com/p/an-llm-will-never-say-thou

Great article. I see it was already submitted once and received zero comments, but it deserves more attention than that.

Re: Slop Cop

#114

Post by VorpalWay »

Aurornis wrote: post #80
Swizec wrote: post #31

Earlier quoted context omitted.

> "I had a shower thought and I asked a chatbot to write five pages of text about it." I don't need prettier words, I need there to be fewer of them? Always judge an author by the length of their text. Decades of insights barely condensed into 200 pages? Great! Hours of thought expanded into 200 pages? Very bad. Same length of text but lands very differently. Same is true for emails, tweets, videos, and even just tal…

> 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…

There is such a thing as balance. For some reason it tends to be very easy to go overboard in either direction.

Also, any metric ceases to be a good metric the moment it becomes a goal.

I have observed both of the above statements in many different contexts, they seem to be (somewhat) universal rules for human society.

Re: Slop Cop

#115

Post by JuniperMesos »

red_admiral wrote: post #109

The rule of three was actually good and common writing advice in the pre-LLM era. There's psychological studies that show 3 is a good number to grab human attention, which is why you have "an Englishman, an Irishman, and a Scotsman walk into a bar" jokes. Even my Algebra professor said that a well-written definition should have three conditions, for example a group is a set with an operation that is (1) associative,…

A group is an algebraic structure, and many algebraic structures are defined as sets with an operation that obeys some number of axioms. It happens that a group is a structure whose operation has exactly three axioms; but a monoid for instance is a set with an operation with just two axioms - it's a group without the "has inverses" axiom - and I don't think this makes the monoid worse than a group in any meaningful way.

Re: Slop Cop

#116

Post by JuniperMesos »

trane_project wrote: post #79

I pasted a blog that I wrote myself and flagged hundreds of patterns. Granted, the article is 15,000 words so some are expected but there are simply too many false positives to make this and any similar tool have any usefulness beyond flagging the most obvious offenders. And looking at its suggestions, they are not very good. People are better developing their own writing style than trusting generic advice meant for…

I did the same thing, and also found the results pretty mediocre. At best it did point out some places I could've dropped a less important word to be more concise, but pretty much any editing will do that (and I do think I tend towards verbosity as a writer; it's a flaw, but it's my organic flaw). Beyond that it was just pattern-matching on sentence structures it thinks are over-used in LLM-generated prose. Even if that's true, it's not a good argument for why I should rewrite a particular sentence in context.

Re: Slop Cop

#117

Post by Angostura »

tombert wrote: post #32
chromacity wrote: post #22

Like the original Grammarly, I think this can be useful for business writing because these tools help you get to the point. Many students are rewarded for using flowery language in school essays, but if you're composing an email or writing a design doc, just optimize for reading time and clarity. But for general use, I think this is misguided. The problem with LLM output is not that it's using em dashes or words such…

Tangential, but I remember when I was studying for the ACT, there was something in one of the practice books that stuck with me. I'm paraphrasing but it was something like "Good writing is clear and easy to understand. It's about communication, make sure you communicate". It was something that I guess I logically knew but hadn't fully realized. I had always tried to be fancy with my writing and pad it out to meet min…

Good writing and good communication is also about keeping the reader engaged and concentrating, however. Even in business writing - for example, how-tos or intranet pages, altering sentence length, using rhetorical questions can be helpful. I'm concerned that tools like this will tend to stamp out useful writing conventions, that were picked up by LLMs precisely because they were useful.

The result? Increasingly homogeneous, boring text.

Re: Slop Cop

#118

Post by kstrauser »

mech422 wrote: post #81
UqWBcuFx6NV4r wrote: post #70

Earlier quoted context omitted.

Anyone over the age of 25 actually developed their writing style before ChatGPT came about. Getting all uppity about these surface-level LLM ‘tropes’ is just stupid. I am thankfully yet to run into a situation where someone with this attitude is actually in a position to be able to negatively affect my life. I’m sure that there’s a correlation. Take the “ew, em-dash” stuff back to Twitter.

Yeah - writing styles have really changed over the years. Last time I ran a business document thru Grammarly, I was told it wasn't written at a 6(8?) grade level and was too complex :-P When I first started out, I was taught you use passive voice in proposals (eg 'a program will be written..' not 'I will write a program...') since you didn't know who was actually going to write it. I can't imagine how that would go o…

Strunk & White said not to use passive voice since, what, the 1920s? “We will write a program”, or “one of us will write a program” works without passivizing it.

Re: Slop Cop

#119

Post by onchainintel »

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?

Re: Slop Cop

#120

Post by jillesvangurp »

foxfired wrote: post #67

One thing I learned is that AI written text is not hard to spot. Usually, when I meet slop, I close it one or two paragraphs in. Although tools like this will become more common, they usually serve to win an argument, or confirm what you already believe. Also, it was painful to learn that my very first blog post I wrote in 2013 is AI generated. But I'm fine with it because I read this: > A short punchy opener (≤10 wo…

If you can spot it, an AI can spot it too. We have a website with some AI generated content (about AI). I added a skill to correct AI slop. Content got a lot better when I put that in place. I actually made codex research slop patterns and it came up with a list of known AI slop linguistic anti patterns. It now fixes its own content using that list. I also put a guard rail in place to do a critical review of all produced content as a final quality gate. That actually catches a lot of baseless claims, and other slop. And there's another skill that ensures we use the right SEO relevant language (a list that is produced by a separate agent).

It's actually starting to generate interesting content based on me giving it a few bullets and ideas. I won't claim it's perfect but it does a decent enough job.

I have my reasons for doing this (we help people set up agentic work flows) and I appreciate that not everybody likes the idea of AI generated content. But I think it will start getting harder and harder to spot AI slop. Basically slop is what you get without guard rails and quality gates. Of course, most people still lack the skills to configure their AI tools properly. Particularly non technical people. But it's not that hard and I bet there are a few handy journalists out there getting better at this. Also, for technical writers this is not going to be optional.

Post reply on HN