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

191–200 of 275 posts

Re: Stop Sloppypasta

#191

Post by SamuelAdams »

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 ...

I do this quite often, but I also instruct Claude to limit its output to 2-3 sentences or paragraphs, depending on the context. Also "Write this for a team of software developers / MBA's" goes a long way too.

I also do the extra step of eliminating things that are not needed, or we review this during backlog refinement.

Re: Stop Sloppypasta

#192

Post by geronimoe »

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 ...

It's weird that there's little to no focus on making AI describe problems coherently for use-cases like this?

Re: Stop Sloppypasta

#194

Post by namdnay »

Gigachad wrote: post #166
dev_l1x_be wrote: post #153

Earlier quoted context omitted.

Some people use AI as they use anything else. Careless, without putting the effort in, making things somebody else's problem. This existed before AI, it just accelerated the stupidity.

Careless people never used to be able to create such absolute volumes of garbage that flood the system. Open source projects used to be able to just have an open PRs system, because the effort to create and submit something is quite hard, it's a natural filter. Now automated agents can flood a project with hundreds of useless PRs that disguise themselves as being real.

I've had exactly the same feeling. Since the beginning of time, it has generally taken more effort to build something than to review it. This is no longer the case, and it completely breaks some processes.

The quick solution is to escalate the arms race, and start using AI to filter the AI slop, but I'm not sure that's a world I want to work in :)

Re: Stop Sloppypasta

#195

Post by dalmo3 »

brobdingnagians wrote: post #173
lesostep wrote: post #170

Earlier quoted context omitted.

Oh, it was! But the guy that generated it insisted that he triple-checked the prose after, and it should be treated as typed by hand I'm pretty sure it would be okay to stop at 5-10 questions, because it was clear he couldn't answer any. But my friend is from a hateful branch, and so she went for humiliation angle of asking for as much clarification as the ticket itself allowed

I have a very similar situation. Except it isn't even a ticket, just an export of a very long "conversation" with ChatGPT with a vague indication that this is what needs to be implemented. When questioned about it, the person insists they completely understood it before but just forgot after a few days. Sometimes the prompts are removed. Lots of contradictory material in it, some doesn't make sense even in context. V…

> person insists they completely understood it before but just forgot after a few days.

I don't doubt this, to be honest.

I have the feeling of learning a lot when coding with agents. New features, patterns, entire languages... It's very satisfactory asking questions and getting answers in as much detail as you want, with examples, etc.

Except I forget it all soon after. Because I didn't put the effort. Easy come easy goes .

Re: Stop Sloppypasta

#196

Post by leekrasnow »

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 additional human input on the matter.”

In such a case, I think that spending extra time to scrub the output of em-dashes or other slop is just virtue signaling that “I am man, not machine”

Re: Stop Sloppypasta

#197

Post by suddenlybananas »

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…

>There is a reason why the title of Dr.Strangelove is "How I Learned to Stop Worrying and Love the Bomb".

Indeed, and somewhat surprisingly some linguists have embraced even this analogy [1] without appreciating the subtext of the title.

https://arxiv.org/abs/2501.17047

Re: Stop Sloppypasta

#199

Post by tyleo »

TBH "The Oracle" personality doesn't always bother me. There's a bunch of stuff that gets asked in corporate chat that makes me think, "does this person know how to use Google?" I think the same can be said for the chatbots at this point.

I feel like we just need the equivalent of "Let me Google That" for LLMs.

Re: Stop Sloppypasta

#200

Post by geerlingguy »

curiousgal wrote: post #111
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.

Worse, I had a guy literally posting screenshots of copilot replies.

Ah the ol screenshot-of-word-doc-in-email for the 21st century
Post reply on HN