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

/Deslop

tahigichigi.substack.com

Post reply on HN
Print view View original

21–30 of 46 posts

Re: /Deslop

#21

Post by greatgib »

piker wrote: post #4

Just don't use LLMs to generate text you want other humans to read. Think and then write. If it isn't worth your effort, it certainly isn't worth your audience's.

What is nice is that sometimes you will just write very badly what you want to say, like a scenario or badly written sentences, and just ask the LLM to reformulate that to be proper nicely written text. But in that case, there are big chances that the stylistic issues described in the article are present despite you having carefully crafted the content.

Re: /Deslop

#22

Post by greatgib »

randomtoast wrote: post #8

You just need to use this list as a prompt and instruct the LLM to avoid this kind of slop. If you want to be serious about it, you can even use some of these slop detectors and iterate through a loop until the top three detectors rate your text as "very likely human."

I'm surprised that there is not a "skill" for that attached to the article.

Re: /Deslop

#23

Post by orwin »

jbstack wrote: post #14
idop wrote: post #10

Earlier quoted context omitted.

Indeed. I have never used an LLM to write. And coding agents are terrible at writing documentation, it's just bullet points with no context and unnecessary icons that are impossible to understand. There's no flow to the text, no actual reasoning (only confusing comments about changes made during the development that are absolutely irrelevant to the final work), and yet somehow too long. The elephant in the room is th…

" Please write me some documentation for this code. Don't just give me a list of bullet points. Make sure you include some context. Don't include any icons. Make sure the text flows well and that there's actual reasoning. Don't include comments about changes made during development that are irrelevant to the final work. Try to keep it concise while respecting these rules. " I think many of the criticisms of LLMs come…

But are you gaining a meaningful amount of time, and are your coworkers that thorough.

Honestly I just don't read documentation three of my coworkers put on anymore (33% of my team). I already spend way to much time fixing the small coding issues I find in their PRs to also read their tests and doc. It's not their fault, some of them are pretty new, the other always took time to understand stuff and their children de output always was below average in quality in general (their people/soft skills are great, and they have other qualities that balance the team).

Re: /Deslop

#24

Post by piker »

greatgib wrote: post #21
piker wrote: post #4

Just don't use LLMs to generate text you want other humans to read. Think and then write. If it isn't worth your effort, it certainly isn't worth your audience's.

What is nice is that sometimes you will just write very badly what you want to say, like a scenario or badly written sentences, and just ask the LLM to reformulate that to be proper nicely written text. But in that case, there are big chances that the stylistic issues described in the article are present despite you having carefully crafted the content.

No, the output is normalized garbage. Don't do this. Delete it instead. If it's worth saying, you'll spend the time to edit your original text.

Re: /Deslop

#25

Post by sorobahn »

greatgib wrote: post #22
randomtoast wrote: post #8

You just need to use this list as a prompt and instruct the LLM to avoid this kind of slop. If you want to be serious about it, you can even use some of these slop detectors and iterate through a loop until the top three detectors rate your text as "very likely human."

I'm surprised that there is not a "skill" for that attached to the article.

There is a pdf with a deslop prompt at the end of the article. Prob the skill definition you’re looking for.

Re: /Deslop

#27

Post by tahigichigi »

jbstack wrote: post #14
idop wrote: post #10

Earlier quoted context omitted.

Indeed. I have never used an LLM to write. And coding agents are terrible at writing documentation, it's just bullet points with no context and unnecessary icons that are impossible to understand. There's no flow to the text, no actual reasoning (only confusing comments about changes made during the development that are absolutely irrelevant to the final work), and yet somehow too long. The elephant in the room is th…

" Please write me some documentation for this code. Don't just give me a list of bullet points. Make sure you include some context. Don't include any icons. Make sure the text flows well and that there's actual reasoning. Don't include comments about changes made during development that are irrelevant to the final work. Try to keep it concise while respecting these rules. " I think many of the criticisms of LLMs come…

OP here. You're absolutely right!

Most people drop a one line prompt like "write amazing article on climate change. make no mistakes" and wonder why it's unreadable.

Just like writing manually, it's an iterative approach and you're not gonna get it right the first, second or third time. But over time you'll get how the model thinks.

The irony is that people talk about being lazy for using LLMs but they're too lazy to even write a detailed prompt.

Re: /Deslop

#28

Post by tahigichigi »

fxwin wrote: post #16
jbstack wrote: post #14

Earlier quoted context omitted.

" Please write me some documentation for this code. Don't just give me a list of bullet points. Make sure you include some context. Don't include any icons. Make sure the text flows well and that there's actual reasoning. Don't include comments about changes made during development that are irrelevant to the final work. Try to keep it concise while respecting these rules. " I think many of the criticisms of LLMs come…

Believe me, I've tried. By the time i get the documentation to be the way I want it, I am no longer faster than if i had just written it myself, with a much more annoying process along the way. Models have a place (e.g. for fixing formatting or filling out say sample json returns), but for almost anything actually core content related I still find them lacking.

I guarantee if you give me your prompt and the output you got I can fix it and get you a 10x better output in less than 5 minutes.

DM me on substack if you don't wanna post it here, I'm honestly happy to help wherever I can.

Post reply on HN