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

131–140 of 169 posts

Re: Slop Cop

#131

Post by ljm »

VorpalWay wrote: post #114
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…

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.

I've also observed the third direction, which is the message storm.

That's when someone breaks down their point into multiple separate messages, one sentence at a time, when a single coherent paragraph or two would have worked. Why send one message when you can send 7 in rapid succession?

It's arguably the most annoying method of communication because it spams your notifications and you have no idea when someone has finished dumping.

Re: Slop Cop

#132

Post by cineticdaffodil »

littlexsparkee wrote: post #41
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…

So many books that could've been an article. I try to save myself time by checking Goodreads but it's not always clear as I'm more critical than the average person. Reading a preview in Google Books helps but you only get so many pages before you're cut off. Appreciate that lately new books are sometimes featured in pubs with an excerpt.

The worst is scifibooks that explore ideas but the authors afraid of literary critics jam in "real" characters with real "drama" to satisfy a crowd who does not get the purpose of the medium, even while they life inside one of those accelerando shortstories now.

Re: Slop Cop

#133

Post by moron4hire »

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…

This is something I've been working on in my own professional writing for years. I used to write very long emails, thinking I was providing insight and detail, but nobody would even bother reading them because it was such a chore.

I consider more than three paragraphs and more than two sentences per paragraph a "writing smell." It's relatively easy now, especially when I realized my predilection for verbosity was actually a symptom of my own insecurity, emotionalism, and indecisiveness.

I try to limit my emails to one, clear, strong point—usually just factual statements—in the active voice, eschewing adverbs as much as possible. The emails almost write themselves now, because there isn't much choice on what to write anymore.

Re: Slop Cop

#134

Post by ljm »

abustamam wrote: post #83
lokar wrote: post #48

Earlier quoted context omitted.

As a senior engineer I spend a lot of time reviewing and approving technical designs, PRDs etc. Over the years the amount of basic copy editing I have to do has really grown. I sometimes feel like I’m removing 20%+ of the text. And that was before LLMs.

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.

Re: Slop Cop

#135

Post by awnist »

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?

Good idea! Nothing special about the Anthropic calls, would be simple to point at local models

Re: Slop Cop

#136

Post by goodmythical »

kstrauser wrote: post #118
mech422 wrote: post #81

Earlier quoted context omitted.

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.

What if the program is to be subbed out?

Just because two guys got together a hundred years ago and wrote some stuff doesn't mean it's worth dedicating a life of writing to.

Let alone decades of arguments supporting the claim that their style guide is at best only useful for a small subset of writing, the two themselves admit that there can be no one universal styling guide in a variety of ways. You can see many examples in the text itself in which the authors seem to forget their own advice.

Consider:

Vigorous writing is concise. A sentence should contain no unnecessary words, a paragraph no unnecessary sentences, for the same reason that a drawing should have no unnecessary lines and a machine no unnecessary parts. This requires not that the writer make all his sentences short, or that he avoid all detail and treat his subjects only in outline, but that he make every word tell.

Which could communicated much more succinctly containing exactly the same information without any extra exposition:

Vigor is concision. A piece should contain nothing unnecessary, just as a drawing has no unnecessary lines [needless repetition](and a machine no unnecessary parts). This requires not that all sentences short be short, but that every word tell.

Or even more succinctly with only the actual message:

Vigorous writing is concise. Concise writing is vigorous (If you're willing to be charitable enough to provide a second example)

That this does not require unnecessary brevity is easily inferred given that the word is "concise" meaning "free from all elaboration and superfluous detail." not "brief" meaning "short". That the writer should follow the advice is made plain by it being presented in a book of advice. The first two sentences alone (if you grant that the second sentence is necessary) contain four repetitions of the same information. If "vigorous writing is concise" then why have we said the same thing five times?

Re: Slop Cop

#137

Post by awnist »

koito17 wrote: post #75

How does this site tokenize text? Split on ASCII whitespace? Inputting Japanese sentences of any length flags the whole sentence as "Dramatic Fragment: A standalone paragraph with ≤4 words".

That's right, its tokenization and fragment rules use fairly simple heuristics that assume whitespace delimited words plus English language/punctuation. Proper CJK support would require language specific tokenization and morphological parsing. Correcting rules like "≤4 words = dramatic fragment" would be difficult. The more complex rules already require LLM roundtrips, so supporting all languages in one pass would need to rely on LLM alone, I imagine.

Which brings up an interesting point - what do these LLM clichés look like in Japanese?

https://github.com/awnist/slop-cop#client-side-instant

Re: Slop Cop

#138

Post by lokar »

tedggh wrote: post #106
lokar wrote: post #48

Earlier quoted context omitted.

As a senior engineer I spend a lot of time reviewing and approving technical designs, PRDs etc. Over the years the amount of basic copy editing I have to do has really grown. I sometimes feel like I’m removing 20%+ of the text. And that was before LLMs.

Ask your team to make their documentation at least 30% shorter just before sending. I don’t remember where I first I read this advice for writing code, but it’s been part of my workflow for several years. It’s an arbitrary number, but it forces you think how to make things simpler. I apply the same principle when packing for travel or hiking.

I once ended up helping (a bit) editing a book (with chapters written by various co-workers). My main contribution was deleting whole chapters. And telling others to make it 50% as long.

Re: Slop Cop

#139

Post by awnist »

rkagerer wrote: post #5

I'm curious how well this thing works, but you need a yardstick to measure it against. The last year or two a burgeoning community of meatspace AI detectors has emerged right here on HN, it might be fun for someone to rank "sloppiness" of submitted HN articles as gauged by comment sentiment vs. this tool to see how well they align.

Good idea, I did test on HN op/ed submissions and likely upgraded my own wetware slop radar in the process

Re: Slop Cop

#140

Post by awnist »

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.
Post reply on HN