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

241–250 of 288 posts

Re: The user is visibly frustrated

#241

Post by recursive »

hbs18 wrote: post #42
apsurd wrote: post #23

Earlier quoted context omitted.

Semi-related, I'm always very put off by how people treat LLMs. Especially coders, seems an instinctive joy comes out to play God. The justification is usually that it's intentionally against the trap of anthropomorphizing, but no I can't help but suspect it's people getting off on power. It's weird. I am always very cordial in my sessions. It's just more pleasant and it's a habit I want to habituate. Great work! Now…

I think it's the same thing as showing mechanical sympathy towards other tools and objects. I've always slightly judged people on how hard they shut doors or how gentle they are with their cars.

You car door doesn't charge you a subscription or sell mined data or give advice generated inside an opaque machine with opaque influences. If I believed that my car door was phoning home like this, I would cut the wire or tape over the sensor. The metaphor doesn't really work too well.

I treat musical instruments with respect. But I might not if they were harvesting my data and trying to sell me subscriptions.

Re: The user is visibly frustrated

#242

Post by eddythompson80 »

Pay08 wrote: post #212
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.

well you know it kept improving. It got pretty good, though everyone moved to full "agentic" changes over autocomplete.

Re: The user is visibly frustrated

#243

Post by _carbyau_ »

fransje26 wrote: post #93
_carbyau_ wrote: post #13

Earlier quoted context omitted.

Screensaver mode. I start typing my password. .. 10s later the password box appears and I have to do it again. Cue exasperated: "You can compute billions of instructions per second and yet I wait for you."

That's not a bug. It's a (safety) feature.

? Curious. In this case, how is sleep 10s a safety feature?

The screensaver should never see keyboard input. And it shouldn't take 10s for the visual changeover - even for Windows.

Happy to read if you've got a pointer for me.

Re: The user is visibly frustrated

#244

Post by scotty79 »

recursive wrote: post #225
scotty79 wrote: post #141

Earlier quoted context omitted.

> 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.

That's the issue. You frame your relationships with people using words like "grace" and "patience".

If you were "good natured", "kind hearted", "understanding" and "nurturing" instead you wouldn't have to "extend" it to "machines" because those are not limited resources you can run out of. Politeness towards AI would come naturally because of who you are. The only thing you could run out of is energy and that's easy to replenish with a bit of sleep and a meal.

And it would lead to better results. Not because there'd be some genuine psychological interaction between you and LLM. LLMs are not machines. They are just a finetuned math equation that tends to give better results when people act nice.

Also it would be better for your own well being because it would reduce your frustration. Both with LLMs and people.

Re: The user is visibly frustrated

#245

Post by moomoo11 »

whstl wrote: post #29
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 don't believe this is a context problem. Claude Opus 4.7 has a very large context compared to itself, but IME it is the worst at following instructions, and completely disregards the (small) preferences prompt, even in the first or second message, even if the messages are just a few characters long. IMO this is entirely a training problem.

Codex compaction is way better imo.

I've had many long-running sessions and it doesn't suffer the same retardation (the act of delaying, slowing down, or hindering progress) that Opus does.

The quality stays consistent and it actually seems to follow the instructions, todos, etc. even after multiple compactions.

Re: The user is visibly frustrated

#246

Post by nemo1618 »

You should not swear at LLMs, for the same reason you should not shout a slur even if no one is around to witness it: You witness it, and witnessing yourself being toxic updates you in the direction of "I am capable of toxicity" and eventually "I am toxic." In other words, it stains your soul.

Re: The user is visibly frustrated

#247

Post by scotty79 »

recursive wrote: post #237
scotty79 wrote: post #146

Earlier quoted context omitted.

I dread people who get abusive with AI, because I know it's only fear that prevents them from being like that with me. Even if only it is the fear of hurting me, it's still terrible because every fear can pass.

I don't understand this at all. If someone hits a nail with a hammer, does that mean they might start hitting people with hammers one day? I'm not afraid of being abusive with humans because I know I'm not going to do it. That's a thing that's in my control.

Depends how they are hitting the nail. If they do it furiously with anger in their eyes, yes.

If they do it to fasten two things together, no.

Emotionally motivated violence is something to be extremely cautious about, regardless of the target.

Re: The user is visibly frustrated

#248

Post by djsavvy »

nemo1618 wrote: post #246

You should not swear at LLMs, for the same reason you should not shout a slur even if no one is around to witness it: You witness it, and witnessing yourself being toxic updates you in the direction of "I am capable of toxicity" and eventually "I am toxic." In other words, it stains your soul.

I 100% agree with you, which is why I try to be polite to the LLMs. Also, on a practical note, I've never seen an agent session go right-side-up after I crash out; the model seems to perform worse than if I just gently guide it.

Re: The user is visibly frustrated

#249

Post by phil21 »

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…

The end result is the goal for most of my home projects these days.

I suppose you could put almost all my stuff under "devops" vs. "development" but the idea is the same.

Recently I "vibe coded" some IoT sensors to monitor my garden environmental parameters, and created dashboards/alerts around them. I could have done all those things myself, but I never would have had the inertia or couple weekends to burn to spin it all up from scratch and teach myself every tiny little nuance.

Now I have a mostly-okay output of some grafana dashboards and HA alerts for soil moisture, and some neat correlation between those sensors plus my irrigation and rainfall data.

Or just opening a chat with AI to use it's "WLED" skill to go change the holiday theme of my permanent RGB lights along the fenceline.

Sure, once in a while I want to drop down and learn a new skill for such projects. But there is already a whole lot of "physical" bits of these projects and the coding/IT work is just the final piece of the puzzle. These days it's much more of a chore than a discovery process to spin up the 516th Ubuntu VM I've configured over my lifetime and configure software to have it do something useful for me.

Same goes with a lot of "glue" type scripts and automations like getting backups all working and monitored across my personal IT infrastructure.

If I'm doing something for the joy of learning these days it's almost always going to be learning a new physical skill like welding or woodworking or something I can immediately see the results of my labor. I guess I'm simply burned out on computers, and find very little novel in what I want to accomplish.

For this sort of thing agentic AI has been eye opening to me. It definitely has informed how I plan to implement some tasks at work for my career, as I've seen the massive amount of time it can save for the tedium. Creative and mission critical stuff? Probably not for some time.

I've also never much been a "love of the game" sort of guy when it comes to programming. It's always simply been a means to an end. The outcomes are what matter to me. I find working with well designed architecture quite satisfying, but beyond that I really don't get some inherent joy in the process. Those late night 3am hacking sessions were always fun to me because of the result I achieved at the end of the process.

Re: The user is visibly frustrated

#250

Post by equinumerous »

Diti wrote: post #121
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…

Claude allegedly uses this RegEx to detect frustration: /\b(wtf|wth|ffs|omfg|shit(ty|tiest)?|dumbass|horrible|awful|piss(ed|ing)? off|piece of (shit|crap|junk)|what the (fuck|hell)|fucking? (broken|useless|terrible|awful|horrible)|fuck you|screw (this|you)|so frustrating|this sucks|damn it)\b/ https://news.ycombinator.com/item?id=47586778

Legend has it that if you can come up with a string that matches all parts of that regex, Claude starts spitting out free credits.
Post reply on HN