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

211–220 of 275 posts

Re: Stop Sloppypasta

#211

Post by duxup »

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…

I work for a small SaaS company.

We’re getting prospective and existing clients emailing us what look like AI generated spreadsheets with features that are miles long that they want us to respond to. Like thousands of lines. And a lot of features that are “what does that even mean??”

We get on a call with them and they don’t even know what is on the spreadsheet or what it means…

Very much a “So you want us to make Facebook?” (Not actually asking for Facebook) feeling.

I fear these horror shows of spreadsheets are just AI fever dreams….

Re: Stop Sloppypasta

#213

Post by GuB-42 »

sillyfluke wrote: post #181
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…

>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. Obviously you're not a golfer. Human sectretaries don't have non-deterministic hallucinations and random critical ommissions in their summaries, which I've witnessed first hand with LLMs. More importantly, if they do you have more deterministic mitigations with them than you do with LLMs, a…

To make things clear, even though I am not a golfer, I have a lot of respect for good secretaries, that's why I said they can do much more than write formal letters. Not only they don't hallucinate like LLMs but they can actually catch mistakes before they happen.

I just wanted to point out the seemingly ridiculous idea of formal communication that none of the interested parties actually read. It is as if two English speakers insisted for the discussion to be in Spanish, and they both brought an interpreter for that.

Re: Stop Sloppypasta

#214

Post by Bridged7756 »

diath wrote: post #110
merrvk wrote: post #108

I had a guy doing this to reply to PR review comments, copying in the comment to the LLM and pasting the response back.

Reminds me of this PR: https://github.com/ocaml/ocaml/pull/14369

That comment chain depicts perfectly my thoughts about LLMs. Yeah, they can generate a lot of code, but someone has to look at all that, and clanker code is more taxing to read than code written by another person which wasn't easy to read to begin with.

Re: Stop Sloppypasta

#215

Post by _zoltan_ »

sbinnee wrote: post #134

As a senior engineer, I am getting extremely tired of reviewing AI slops. Today at work I have decided that I just have to build a POC project from scratch. I spent 2 weeks to review the code, to log the process, and to build toy examples to make my argument clear that some (actually most) parts were not working. The funny thing is that I know my manager got this “working” within a week with Claude. I had to spend 2…

Reading this, honestly, I'd say the problem is you then?

Velocity is everything.

Re: Stop Sloppypasta

#216

Post by _zoltan_ »

elric wrote: post #124
febusravenga wrote: post #115

Earlier quoted context omitted.

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 my current company, people who don't use enough of their token budget get a stern talking-to from manglement ...

as it should be?

Re: Stop Sloppypasta

#217

Post by zombot »

There is no hope of stopping the deluge of sewage. The convenience of generating infinite amounts of waste with the press of a button will trump all other considerations.

Re: Stop Sloppypasta

#218

Post by bagacrap »

leekrasnow wrote: post #196

I disagree with the premise of automatically dismissing sloppypasta just because it is verbatim LLM output. The sender could hypothetically have spent real effort in the chat interaction that led up to the ctrl-C moment, could have spent real effort weighing all the points raised and thought to themselves “this is all valid stuff to consider, let me forward it to my colleagues and see what they think for some additio…

If you honestly think that the em dashes are the problem, I'm sure you could tell chat to scrub those for you.

Re: Stop Sloppypasta

#219

Post by projektfu »

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…

One of these days, Alice....

Re: Stop Sloppypasta

#220

Post by bagacrap »

Aeolun wrote: post #29
OptionOfT wrote: post #16

It's very weird how many people take the output of ChatGPT/Gemini/Claude as gospel, and don't question it at all. It's also very impolite to dump 5 pages of text on someone, because now you're asking _them_ to validate it. When I ask a question in Slack I want people's input. Part of my work is also consulting the GPTs and see if the information makes sense. And it shows up the most with people who answer questions i…

I don’t mind this so much if they don’t know anything about the subject themselves. What bothers me is when they then copy it at domain experts as if it makes them qualified to talk.

I have witnessed people arguing with their own lawyers by pasting LLM generated output. That said, lawyers do love to argue so maybe it's fun for them.
Post reply on HN