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

41–50 of 288 posts

Re: The user is visibly frustrated

#41

Post by anonzzzies »

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 notice the same. Like you I am not even sure if it really helps, however, every day I find occasions where I see Opus will never do it correctly even though I calmly explain; swearing then suddenly fixes it. I had some issue yesterday where opus kept blaming the api for not sending some field while I knew it was there ; I showed it json, logs etc but it kept repeating that there must have been a glitch; frustration built, I called it all kinds of things in one sentence and the next solution was the right one. This after 10 similar misguesses. It was one of those increasingly rare cases where I should have just done it myself, but I can never know going in how stubborn it will be in continue blaming the (obviously) wrong thing. The around 11 prompts to get to the answer were in a /clear opus 4.7 context (1m) on xhigh.

Re: The user is visibly frustrated

#42

Post by hbs18 »

apsurd wrote: post #23
ilitirit wrote: post #19

I've often wondered if LLMs can suffer from psychological abuse in symptomatic ways. Not literally of course, but for example, if you berate the LLM by calling it stupid, or useless, does that modify its behaviour negatively? Part of me think it does, but I don't really have any evidence for this. Maybe a fun weekend research topic.

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.

Re: The user is visibly frustrated

#43

Post by whstl »

apsurd wrote: post #38
whstl wrote: post #29

Earlier quoted context omitted.

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.

Isn't a large context window still a problem though? At the upper bound, the more you put in the more each sentence washes out within that window?

I’m not talking about large amounts of text, I’m talking about a couple sentences back and forth.

It disregards things like “no follow up questions”.

Haiku, for example doesn’t.

This bias is a very human thing, actually now that I think about it. You just disregarded the “even if the messages are just a few characters long”. :)

Re: The user is visibly frustrated

#44

Post by Foskya »

MaxikCZ wrote: post #10

> drop the human pretense entirely. Make the agent sound clinical, robotic Id pay to be able to reliably set LLMs to this mode, but ofc because LLMs are taught on corpus of HUMAN text, they always, sooner or later, return to the good old penpal mode. Also, in Claude Desktop app, I ask to edit a file, it complains it cant access files, I then realize im in Chat and not Code interface. Why cant such a smart machine fig…

> Id pay to be able to reliably set LLMs to this mode,

You can do it for free. Just give it instrucitons to avoid emotional tones and flattery and it will sound a lot more robotic. If you look into other examples I'm sure you will find other good instructions based on your need

Re: The user is visibly frustrated

#45

Post by fc417fc802 »

apsurd wrote: post #23
ilitirit wrote: post #19

I've often wondered if LLMs can suffer from psychological abuse in symptomatic ways. Not literally of course, but for example, if you berate the LLM by calling it stupid, or useless, does that modify its behaviour negatively? Part of me think it does, but I don't really have any evidence for this. Maybe a fun weekend research topic.

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 am always very cordial in my sessions. It's just more pleasant and it's a habit I want to habituate.

I think it also produces better results. I have noticed that result quality is extremely sensitive to both the framing and tone of what I say. For example "X is the wrong approach, rework that" versus "will X have any performance implications". Personally I find that steering it towards an exploratory academic tone tends to produce better outcomes.

While unfortunate, I think that's more or less expected since much of the training data is human generated text. Looked at that way, would you rather contract the average regular on twitter or the average author of papers published in CS journals? (Somehow that ended up sounding eerily like summoning in a high fantasy setting.)

Re: The user is visibly frustrated

#46

Post by savolai »

anonzzzies wrote: post #41
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 notice the same. Like you I am not even sure if it really helps, however, every day I find occasions where I see Opus will never do it correctly even though I calmly explain; swearing then suddenly fixes it. I had some issue yesterday where opus kept blaming the api for not sending some field while I knew it was there ; I showed it json, logs etc but it kept repeating that there must have been a glitch; frustration…

Fascinating. Projection/antropomorphism or actual human fawn-like survival mechanism trait-ish? It should be possible to test this empirically.

Re: The user is visibly frustrated

#47

Post by alexwwang »

Accidentally I am working on this. I noticed the agent keeps making same mistakes and that annoyed me so much. What I am trying to do are: 1. Revise my skill prompt to level up the signal-noise rate so the agent would understand what should do clearly and correctly. 2. I am building up a status machine to monitor the agent’s work so it could stop the agent from going forward with a mistake automatically.

The first approach does work as far as I keep on iterating. The second is based on a project I once tried to let agent reflect its mistakes and deposit those experiences and learnings from mistakes and reflections. I named it Aristotle and you can find it on GitHub.

Shouting at the agent could only correct the current mistake but cannot prevent the next one.

Re: The user is visibly frustrated

#48

Post by alentred »

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…

Reminds me of this study: https://arxiv.org/pdf/2510.04950 . It demonstrates that being "rude" or "very rude" increases the accuracy of the results. A dubious but very fun read. The prompts in Table 1 (top of page 3) are awesome. I am sure they tried other prompts, but didn't include them to the paper.

Re: The user is visibly frustrated

#49

Post by silversmith »

anonzzzies wrote: post #41
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 notice the same. Like you I am not even sure if it really helps, however, every day I find occasions where I see Opus will never do it correctly even though I calmly explain; swearing then suddenly fixes it. I had some issue yesterday where opus kept blaming the api for not sending some field while I knew it was there ; I showed it json, logs etc but it kept repeating that there must have been a glitch; frustration…

So the correct strategy is a global CLAUDE.md with couple lines of colourful "you best behave or else" texts, so all your prompts get routed via the frustrated path?

Re: The user is visibly frustrated

#50

Post by stingraycharles »

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.

[dead]
Post reply on HN