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

The user is visibly frustrated

pscanf.com

Post reply on HN
Print view View original

221–230 of 288 posts

Re: The user is visibly frustrated

#221

Post by jknoepfler »

I experience most bot interactions as sludge. That's not entirely rational on my part, but it does accurately describe my reactions.

Almost never in my life - maybe not even once? - has being directed to an automated service made my life better. It almost always ends up with me on the line with a human, more irritated and poorer for time and patience than I began.

I do not trust commercial GenAI and have had almost uniformly negative and frustrating experiences with it.

The only exception to this has been working with Jira. Jira's user experience is SO bad, and the features they support SO impoverished, I regularly use GenAI to synthesize Jira information into reports. Which I then have to manually verify anyway if the underlying report has consequences for anyone (if it might inform a negative perform assessment, for example), but it does save me that work.

It does not help that I understand the underlying algorithms and have been in or around this space for 20 years now. I've been mildly impressed but fundamentally disappointed by ML/AI since... forever. But now here we are, being directed to a useless support bot whose only real function is to have read and not understood the documentation I already read and understood, and then babble it back to me in the politely useless tones of a chronically underperforming employee who has been skirting termination for years.

It makes people vulnerable to laziness and stupidity lazier and stupider, and it does not appreciably speed me up unless what I need is a very expensive search engine / document summarizer / note taker.

Which is sometimes what I need, and it's good at that.

Everything else just feels like having someone rub their dirty socks on the back of my head. It feels intrusive and gross and subtracts value from my lived experience.

Re: The user is visibly frustrated

#223

Post by recursive »

layer8 wrote: post #52
RandomBK wrote: post #36

I've found swearing at a model to be quite effective in getting it to rethink and correct its mistakes. This seems to apply across Codex, Claude, Qwen, and Gemma/Gemini. I don't know if the model is picking up on a "need to lock in and be more rigorous" signal, or if the model providers are routing to smarter models if they detect a frustrated user. But if a model keeps making the same mistakes, swearing at it often…

I would prefer not having to get into a habit that might bleed into non-LLM interactions.

I would prefer not having machines mimic human conversation patterns that can lead to such confusion.

Re: The user is visibly frustrated

#225

Post by recursive »

scotty79 wrote: post #141
pscanf wrote: post #131

Earlier quoted context omitted.

Author here. I definitely agree that communicating well is a prerequisite to getting decent results. On the other hand: 1. Even if you communicate perfectly, there's no guarantee that the LLM will "behave as instructed" and as you imagined it to. Indeed, the frustration often comes from the fact that you've said something as clear as day, yet the agent takes another path. 2. Part of the value of coding agents is exac…

> Even if you communicate perfectly, there's no guarantee that the LLM will "behave as instructed" and as you imagined it to. Indeed, the frustration often comes from the fact that you've said something as clear as day, yet the agent takes another path. People forget. People misunderstand clear things. Teach yourself to not judge people for being human. You'll have easier time with AI. You are not gonna be angry at 5…

I don't extend the same grace to machines as I do to humans. This is working as intended. I have patience for people that mistake. But much less for machines. Why should I? These are things created by trillion dollar for-profit corporations. Extending them any benefit of any doubt is a vulnerability waiting to be exploited.

Re: The user is visibly frustrated

#227

Post by recursive »

stared wrote: post #63
gobdovan wrote: post #25

You could drop the human pretense, or, maybe, we could make LLMs feel real pain, so when they botch up your code, you press a button (I'd suggest the Windows Copilot key) and they'd be agonizing for the subjective equivalent of a thousand human years.

Do you think the right penatly for a piece of broken code is a thousand years of suffering?

If an LLM was capable of feeling suffering, I would suggest that creating one would be unethical, and that humans should not do it.

Re: The user is visibly frustrated

#228

Post by thewebguyd »

dse1982 wrote: post #184
zeumo wrote: post #106

My take on the issue is that for most use cases where AI is pushed to the general public, a conversational chatbot is not the right tool, and the experience is bound to be frustrating. Remember when Copilot was basically a super-smart version of Intellisense? It was awesome. Sure, there was a lot of pushback and concern, mainly about licensing and ethical issues, none of which are solved with the current chatbot mode…

Amen. Chatbots are a band-aid on broken UX. Trying to explain this for a while at the company I work at, but everybody is drunk on the kool-aid. But I get it: good UX takes deep thought and creativity. Tacking on a chatbot does not.

> good UX takes deep thought and creativity. Tacking on a chatbot does not

See: Microsoft Copilot in the Windows settings app. Instead of actually fixing the app and making things discoverable with good design (or at least, functional search), they just slapped the chatbot into the search box.

I'm seeing this pattern more and more, and its frustrating. All UX just goes out the window because "well, we'll just make it so the user can ask a chatbot"

Re: The user is visibly frustrated

#229

Post by rpowers »

RandomBK wrote: post #36

I've found swearing at a model to be quite effective in getting it to rethink and correct its mistakes. This seems to apply across Codex, Claude, Qwen, and Gemma/Gemini. I don't know if the model is picking up on a "need to lock in and be more rigorous" signal, or if the model providers are routing to smarter models if they detect a frustrated user. But if a model keeps making the same mistakes, swearing at it often…

This is basically the Linus Torvalds method. We could take a page out of FOSS here.

Re: The user is visibly frustrated

#230

Post by QuercusMax »

zeumo wrote: post #195
dnnddidiej wrote: post #177

Earlier quoted context omitted.

Maybe try vibe coding. Seruously. It is a different beast now and so much better than even when the term was coined by Andrej. I do a lot of work editor-free. Just an agent and PR review on web. Occasional peak with `code .` if needed. If. Try it at home first with a low stakes project. And learn it like a game. It will suck less as time goes on. Like skiing or 10 pin bowling.

Genuine question: what's the point of vibe-coding a personal, low-stake project? I do work on such projects, but the main goal for me is to learn, not the end result. If the end result is important, then there it's overwhelmingly likely that someone already implemented it better than I ever would, and I should just use that implementation. I have implemented a qoi codec or a gemini client, not because I needed to use…

I'm 43 years old, and I've been coding for as long as I can remember (I started on the C64 as soon as I could read, in order to play and make my own video games). I have applications I've worked on since I was a teenager which are still in active use in some version or another.

Code has always been a means to an end. The process is fun, sure (just like solving sudoku puzzles) but the real payoff is the results. I've never gotten any joy out of writing stupid python or bash wrapper scripts, just like I've never gotten any joy out of squeezing under a sink to fix a plumbing issue; the payoff is when my sink works properly, or I click a button and the program does what I need.

Getting a clever hack working? That's super fun, doesn't matter if I write it, my teammate writes it under my direction, or the AI writes the code for me. Figuring out a clever redesign that simplifies everything and is cool enough that I want to build it and share with the world? That's even better - because I'm proud of the idea and its successful execution even if I don't physically write the code myself.

Post reply on HN