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

81–90 of 288 posts

Re: The user is visibly frustrated

#81

Post by arcanemachiner »

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…

Personally, I have found that Claude absolutely shits the bed if I am rude to it like that.

Qwen seems to handle it okay, though, and will course-correct when encouraged with excessive profanity.

Re: The user is visibly frustrated

#82

Post by gobdovan »

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?

Well, the problem is that current LLMs are stateless, so a thousand subjective years is not well-defined. Without continuity of experience, persistent memory, engineered aversive stimuli and without updating weights meaninguflly during the punishment interval, we are merely doing the equivalent of simply updating a model to believe it just suffered a thousand years. Only once we have all these right ingredients we can empirically determine whether a thousand years is excessive, insufficient, or the local optimum for reducing Claude overwriting that damn CSS color palette.

Re: The user is visibly frustrated

#84

Post by anal_reactor »

aa-jv wrote: post #74

Its kind of astonishing to see years of traditional software engineering practices being tossed aside in the rush for the Latest Cool New Thing™ ... have people really forgotten that you have to apply a workflow to software development, in order to have quality software? You don't just write it, compile it, run it and ship it - do you? Surely, in the rush to become as agile as possible, folks haven't forgotten their…

> You cannot just ignore natural laws and assume, because you 'know better', your software will 'be better'. And whether we like it or not, all software follows a philosophically natural law, which has evolved over decades of human attention. Ignoring these natural laws (...) is only gonna get you butt-hurt, kiddo.

If only you could just read these words back to yourself. Designing perfect software is NOT the case 90% of the time. 90% of the time the entire purpose of software is to facilitate business so if business says "prioritize speed over quality" then you shut up and do exactly that.

Imagine owning a bakery and telling the employee "we need more donuts faster, stop spending ages decorating every single donut like god damn Picasso, just do whatever and move onto the next one, customers are waiting" but instead the guy goes on a rant that nooooooooo only the perfect donuts should be sold, if the glazing isn't perfectly distributed it ruins the flavor profile, which is a real disgrace to the art of making donuts... bro this fast food, stfu and make the donuts faster, we have ten H-1B Donut Artists waiting if you don't like your role.

Re: The user is visibly frustrated

#85

Post by carsareok »

JSR_FDED wrote: post #59
bad_username wrote: post #3

> furiously hammering on my laptop “WHAT THE FUCK DID YOU DO???”. The recipient of these tirades is, you might have guessed, a coding agent. It’s completely pointless, I know. I believe it's worth than pointless. IMO adding such things to the context "configures" the AI to reproduce the statistics of conversations where people swore, shouted, and were unprofessional (despite the alignment runing and all that), where…

Why would you deprive the LLM of a signal that indicates how badly it screwed up?

Because it's a completion engine and has no notion of "signals".

Swearing was in the texts they were trained on to complete token by token. I suspect it weren't texts with a lot of high-quality reasoning.

Re: The user is visibly frustrated

#86

Post by mchinen »

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 interesting, because in the leaked code, it was found that they detected simple swearing keywords for analytics that get sent to Anthropic, but also had directions to keep the behavior the same for claude. I also have the feeling a 'wtf' does something, but it does feel good and might just be placebo, because 'that is still wrong' sometimes works the 4th time too. Or maybe they changed something.

Re: The user is visibly frustrated

#87

Post by willtemperley »

Is it realistic to have multiple coding agents hammering out piles of code and expect good results?

Genuine question, is it worth it? I just find that using Claude via the web interface gives such good results I don't want to spend time messing with my tooling. Neither do I need more code to be generated than I have already.

One person and one LLM building one component at a time seems optimal to me.

Re: The user is visibly frustrated

#88

Post by throw310822 »

carsareok wrote: post #79
rpcope1 wrote: post #39

Earlier quoted context omitted.

That's been one of the gravest re-realizations I've noticed watching coworkers trying to pick up "agentic" coding: they often just break down into "just fix it" or "why is this broke". I've noticed that even though supposedly there's training or some sort of work done to make the agent work better with unclear or ambiguous grammar or bad structure, it feels like the quality changes palpably when you talk in clear wel…

Yes, I have definitely witnessed this as well. I think, I hope, this will be fixable to some degree, but at this moment I believe it's best to communicate in Queen's English and try to maintain the level of clarity of thought you expect of them in return. My pet theory is that actual real conversations they were trained on with bad grammar and spelling are in general relatively starved of proper reasoning. By talking…

Also, quite simply, the output is a function of the requirements and the context. If you can't communicate clearly what the situation is and what you want, what do you expect the LLM to do, read your mind?

Re: The user is visibly frustrated

#89

Post by jofzar »

Interestingly to me, the problem I always find is that you will make a suggestion, the AI will go through a thinking loop, come to the exact wrong conclusion then blast out tokens make the solution to their own conclusions.

I honestly wish there was more "I'm not sure what you meant can you clarify this part" more often. It feels like I want a "confidence in itself slider"

Re: The user is visibly frustrated

#90

Post by carsareok »

throw310822 wrote: post #88
carsareok wrote: post #79

Earlier quoted context omitted.

Yes, I have definitely witnessed this as well. I think, I hope, this will be fixable to some degree, but at this moment I believe it's best to communicate in Queen's English and try to maintain the level of clarity of thought you expect of them in return. My pet theory is that actual real conversations they were trained on with bad grammar and spelling are in general relatively starved of proper reasoning. By talking…

Also, quite simply, the output is a function of the requirements and the context. If you can't communicate clearly what the situation is and what you want, what do you expect the LLM to do, read your mind?

Oh yes, the part where actual crucial non-derivable information was left out certainly comes into play as well. I suspect many people underestimate the sheer magnitude of implicit cultural and organizational knowledge they and their colleagues carry with them. It's always part of their context in everything they do, so to speak and they expect the "bots" to carry this as well (without giving it to them).
Post reply on HN