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

211–220 of 288 posts

Re: The user is visibly frustrated

#211

Post by alehlopeh »

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…

As you stated, the point is the end result.

Re: The user is visibly frustrated

#212

Post by Pay08 »

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…

> Remember when Copilot was basically a super-smart version of Intellisense? It was awesome.

I have only used the Copilot completion for C#, but it was absolutely awful and a net negative not just compared to IntelliSense, but compared to the most basic autocomplete algorithm imaginable. I turned it off after a day.

Re: The user is visibly frustrated

#213

Post by KaiShips »

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…

[flagged]

Re: The user is visibly frustrated

#214

Post by epestr »

alentred wrote: post #119
morpheuskafka wrote: post #68

Earlier quoted context omitted.

Wasn't it posted a few weeks ago that the frontend code for Claude or maybe Gemini or one of them had a swearing-at-model classifier that passed a flag to the backend? (Not sure why it was even done in frontend, but it was.)

Oh. What does it do? Do you have a link? I am very curious about it.

From above: https://news.ycombinator.com/item?id=47586778

Re: The user is visibly frustrated

#215

Post by kolinko »

wcoenen wrote: post #4

The UX problem is elsewhere I think. Many users probably don't realize that the agent's context window is limited, and that clever compaction is happening regularly to make it seem infinite. But that necessarily means the agent has to forget stuff. As a result, users will keep reusing the same coding or chat session again and again. While it would be better to start fresh for unrelated tasks.

I think the post author is smarter than that.

I usually work with sessions Even with a fresh session, if you bump into one of these things, it will lead you into circles that will be very hard to break out of. And swearing helps a bit.

Re: The user is visibly frustrated

#216

Post by JamesSwift »

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…

Since the source code leaked showed they key off of swearing to trigger certain behavior, I actually intentionally swear when running into things like insufficient thinking and/or hallucinations. It also unironically makes it easier for me to grep later to run analysis on how often its happening.

Re: The user is visibly frustrated

#218

Post by mattlondon »

I hit this wall quite hard a couple of months ago. I was getting extremely frustrated and feeling incredibly burnt-out and frankly quite unsettled by how I was behaving and ultimately spiralling into something of a furious rage-depression that would totally sour my entire day at work and at home. I've seen the canned "crisis response" now more times than I'd care to count.

I changed the system prompt to ask it to only ever use 3rd person, and to never present a human identity or persona. Act like a tool would, not a conversation etc. At the same time I also tried to drop asking it things in a conversational tone myself and give it more direct instructions without any polite/florid extra words, and provide bullet points for what I wanted.

I think this helped somewhat, and helped me to break the spiral a bit. I used it for a week or two before I turned it off again. I still get frustrated, but I tend not to spiral quite so much and it doesn't ruin my day any more.

I still get annoyed as hell by it always having to have "the last word" when I am berating it though (e.g. it will cheerily respond "I hear you. I'll be here and ready when you are!" in response to a prompt from me like "JUST FUCKING FUCK OFF AND FUCKING DIE I FUCKING HATE YOU." etc. Sigh).

Re: The user is visibly frustrated

#219

Post by smcg »

streetfighter64 wrote: post #64
em-bee wrote: post #2

behaving like a human is not the problem. behaving unpredictably is. not doing what i expect, or rather not being able to define what i can expect is what's bothering me. but the real kicker is: getting frustrated creates stress, that's unhealthy and makes for a hostile work environment. as much as i sympathize with the idea that AI tools can be more helpful than they cause pain, i am simply not interested in working…

Incredibly privileged take to claim that using Windows is somehow beneath your "dignity". Do you have any idea at all of the kinds of jobs people are doing in the real world? Imagine the daycare worker taking care of your kids or the truck driver bringing your food saying "getting frustrated creates stress, that's unhealthy and makes for a hostile work environment".

Bob forbid someone have standards

Re: The user is visibly frustrated

#220

Post by 0xffff2 »

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…

Plenty of people have personal projects where the purpose is the end result. One small recent example of my own, I'm a long-time Garmin watch user. I struggled with learning all of the details of their custom language, runtime and SDK in the pre-LLM world. With agentic AI tools, it was dramatically easier to write a watch face that looked the way I wanted. From there, I very much did learn a lot and do a lot of re-writing and tweaking to make the code actually somewhat good, but the custom watch face was the point for me. I really couldn't care less about Garmin's esoteric tech stack. The only reason I bothered with everything after the vibe-coding step was to try to optimize power consumption where I could.
Post reply on HN