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

Stop Sloppypasta

stopsloppypasta.ai

Post reply on HN
Print view View original

241–250 of 275 posts

Re: Stop Sloppypasta

#241

Post by vharuck »

GuB-42 wrote: post #175

You can use AI to make a summary of these AI-generated walls of text. We are getting to this weird situation where instead of Alice sending a message to Bob, Alice sends the message to her AI, which sends it to Bob's AI, which then tries to recover Alice's original message. To be fair, I don't think it is an AI problem, more of a quirk of formal communication, the same happen with human secretaries. For example, I wa…

>We are getting to this weird situation where instead of Alice sending a message to Bob, Alice sends the message to her AI, which sends it to Bob's AI, which then tries to recover Alice's original message.

Somebody's going to revolutionize how we use AI by creating an algorithm where the output of an AI is modified so that it has fewer tokens but results in a similar-enough input for another AI to respond to. Like dropping purely syntactic words or using small synonyms. It'll be a bizarre shorthand that makes no sense to humans, riddled with artifacts of the model.

Or we're going to realize that creating output with one AI for another to ingest is needlessly breaking a session into different pieces. But that would mean a lot of professional emailers getting optimized out.

Re: Stop Sloppypasta

#242

Post by verdverm »

sawsimilar wrote: post #69
verdverm wrote: post #6

Earlier quoted context omitted.

I've had some luck pointing out where the AI is wrong in their sloppypasta, delicate as one can. Avoiding shame or embarrassment can be a powerful motivator. The most interesting incident for me is having someone take our Discourse thread, paste it into AI to validate their feelings being hurt (I took a follow up prompt to go full sycophancy), and then posting the response back that lambasted me. The mods handled tha…

Ooh, I saw a very similar situation. User went on AI and asked "Which user was disrespectful first" to dunk on another. The person being targeted just prompted the same AI with "Which user has thin skin" and instantly the AI turn on the other person. Then the moderators got involved and told the first guy to stop using AI as a genital pleaser.

I asked Gemini what it thought, in one of the modes, it said bringing an Ai to a discussion is like bringing a gun to a knife fight, that using AI was like having a rhetorical weapon and advantage in what everyone thought was a human to human forum.

Re: Stop Sloppypasta

#243

Post by pixl97 »

mschild wrote: post #159
asplake wrote: post #142

Earlier quoted context omitted.

Is tossing stuff over the fence considered ok now? Review the slop with the person that submitted it.

> Is tossing stuff over the fence considered ok now? Has been for a long time unfortunately. AI didn't create this behaviour but certainly made it easier for the other side to do it. > Review the slop with the person that submitted it. Alternatively, mark them as "Needs Work" if you can. But yes, put the ball in their court by peppering them with questions. Maybe they will get the hint.

>Has been for a long time unfortunately.

Yea, this is so annoying and AI has only grown the problem.

On the support side of things I love when the customer says "your documentation doesn't work like the product".

Re: Stop Sloppypasta

#244

Post by whstl »

czhu12 wrote: post #96

I’ve encountered an even more nightmarish version of this recently: ai generated tickets. Basically dumping the output of “write a detailed product spec for a clinical trial data collection pipeline” into a jira ticket and handing it off. Doesn’t match any of our internal product design, adds tons of extraneous features. When I brought this up with said PM they basically responded that these inaccuracies should just…

Oh boy, do I have a story about this.

I had a PM that was unable to work without AI. Everything he did had to include AI somehow.

His magnum opus was 30 extremely large tickets that had the exact same text minus two or three places with slight variations. He wanted us to create 30 website pages with the content.

The ticket went into details such as using a CDN, following the current design, writing a scalable backend, test coverage, about 3-4 pages per ticket, plus VERY DETAILED instructions for the QA. Yep: all in the same task.

In the end it was just about adding each of the 30 items to an array.

I don’t know if he knows, but in the end it was this specific AI slop that got him fired.

Re: Stop Sloppypasta

#245

Post by shimman »

eucyclos wrote: post #104
bandrami wrote: post #98

Earlier quoted context omitted.

Everybody wants to use LLMs to produce things and absolutely nobody wants to consume the things that LLMs produce and this is the fundamental reason this is all going to collapse unless we find a way for producers to pay consumers to consume their LLM output.

Gotta disagree. I've found several great new YouTube channels that clearly use ai for everything but the script writing. I assume it's an enthusiastic and smart niche expert who lacks the charisma to make videos in addition to doing the research. In very glad ai is filling in those people's weak spots.

What are these youtube channels, care to share their names?

Re: Stop Sloppypasta

#246

Post by TranquilMarmot »

dminik wrote: post #130
czhu12 wrote: post #96

I’ve encountered an even more nightmarish version of this recently: ai generated tickets. Basically dumping the output of “write a detailed product spec for a clinical trial data collection pipeline” into a jira ticket and handing it off. Doesn’t match any of our internal product design, adds tons of extraneous features. When I brought this up with said PM they basically responded that these inaccuracies should just…

Yes. My Jira tickets used to be almost empty, but all of it was useful info. Now, my Jira tickets are way too long. The amount of useful info has also gone down. Talk about an AI induced productivity increase ...

We went from Jira tickets with one or two sentences, "Implement feature X. Here are some caveats: (simple bullet points, a few words each)" to literal _pages_ of full-on unreadable garbage.

Re: Stop Sloppypasta

#247

Post by graypegg »

Totally agree, except for the "AI Ghostwriter" framing. I'm at least fine with someone passing off LLM output as their own, because the hidden social contract that wraps that situation is I assume you read it and agree with what it said.

If you tell me that an LLM wrote it, I will stop reading because I assume the only reason you'd tell me that is YOU want to hedge your bets about it being wrong, so it's clearly not worth my time if you don't even believe it.

However, if I don't know, then I will take it at face value. People can get LLMs to output sensible text and facts, so I expect the implementation detail of "used an LLM" to be hidden from me. If you can't do that, I will think of you as a low effort writer that sprinkles in sloppy rhetorical devices and lists of nothing into your massive multi-paragraph messages, but I'll assume that's YOUR taste. If something happens to be wrong in it, it's because YOU didn't know it was wrong.

Re: Stop Sloppypasta

#248

Post by artyom »

febusravenga wrote: post #115
artyom wrote: post #102

I find "sloppypasta" extremely useful. Since I've been in charge of people and teams for years, it's a clear signal of who I should get rid of.

In my company, overuse of LLm and sloppy pasta is feature of those that you can't fire. For me it destroyed company as aligned group of people, at C level, it's just bazaar of drones throwing AI slow at each other.

> at C level, it's just bazaar of drones throwing AI slop at each other.

I don't think it changed much from before LLMs. it's just that the slop is now automated.

Re: Stop Sloppypasta

#249

Post by nvardakas »

david422 wrote: post #235
nvardakas wrote: post #139

Earlier quoted context omitted.

[dead]

My teammates hit the generate PR button. I'm not reading that, it's a summary of the changes that I am _already_ going to be looking at, wrapped in some flowery language about being "better architecture, cleaner code" etc. So those PRs may as well not have a description at all as far as I'm concerned.

[dead]

Re: Stop Sloppypasta

#250

Post by madrox »

lich_king wrote: post #93
madrox wrote: post #48

Earlier quoted context omitted.

Yet how are the alternative ways of thinking about it better? Spending your time angry about what others can do? In any era, that’s a poor life philosophy. The problem is the same as it has always been. Figure out how to use your time and attention effectively,

A sufficient number of people being angry about something is how you end up with social norms. These norms will shape how the technology is used. Conversely, if your take is that there's no point being angry and we should just take it in stride, that just emboldens the producers of slop.

You're reading too much into my words if you think I'm suggesting we should take it in stride.

I think we should accept that trying to enforce social norms is a waste of time as that will only work on the politest part of the internet. Instead, focus on what you can control: better mechanisms for managing your attention and time.

Post reply on HN