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

151–160 of 288 posts

Re: The user is visibly frustrated

#151

Post by cyanydeez »

silversmith wrote: post #49
anonzzzies wrote: post #41

Earlier quoted context omitted.

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?

there already is a global claude using any cloud model is a high probability that theyre context stuffing trying to curate output for the normative use cases. see "dont talk about goblins"

Re: The user is visibly frustrated

#152

Post by cadamsdotcom »

another-dave wrote: post #101
cadamsdotcom wrote: post #40

You need to automate the pointing out of mistakes. Create your own linters, your own check scripts. Hook them to git pre-commit, either yourself or with husky or python pre-commit. The agent should never finish its work with dumb mistakes still in it. If it does.. you need more checks. Anything repetitive should be automated - even slapping your forgetful coding agent on the wrist…

I really wish there was a "pre prompt" hook natively. As in, before the agent releases control back to me to prompt it again, it runs the hook. I have a pre-push hook that runs all lint/prettier/typechecks/tests etc. These are all clearly signposted in the project, the AGENTS and CLAUDE files are set to run them. Still though, I'll get it saying "All done" and then it'll fail something basic like formatting when I go…

Ask it in your prompt to run pre-commit and the tests when checking things are good.

You can also add a plan exit hook to Claude Code - mine has like 150 bullet points about what I want to see in plans. The first run blocks (exit 2 with a message about what’s expected in a plan); the second run always goes through. So the agent is given plan feedback exactly once and told to go back and make it better. Anything I have to say to it in response to a plan it generates, I think hard about (or ask the agent about) and add that as a new bullet point - and then the plan exit hook is 151 bullet points and I never have to tell the agent that thing again. Working great so far!

Re: The user is visibly frustrated

#153

Post by SecretDreams »

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.

But what if it works to also motivate things other than LLMs?!

Re: The user is visibly frustrated

#154

Post by ourmandave »

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

Half of those are my pronouns!

Re: The user is visibly frustrated

#155

Post by jLaForest »

knollimar wrote: post #137
roel_v wrote: post #124

Earlier quoted context omitted.

I only used Claude a bit, but one of the things I dislike about it, is that it starts to 'push back' when you swear at it, saying things like 'if you continue like this, I won't be able to work with you' and such. I'm like MF'er you're a token prediction algorithm, what are you talking about, and it just makes me irrationally dislike it more. Codex otoh just lets you vent and straight up ignores such outbursts.

I literally type "MF'er you're a token prediction algorithm don't lecture me" and then it behaves

Yea I've definely called it an auto complete clanker a few times and it's never given me any backtalk

Re: The user is visibly frustrated

#156

Post by eithed »

silversmith wrote: post #49
anonzzzies wrote: post #41

Earlier quoted context omitted.

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?

That will not work - you end up with Claude being ADHD and not following any guidelines.

Skills do work, as they ground the agent with constrained context for the task it's performing

Re: The user is visibly frustrated

#158

Post by 21asdffdsa12 »

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…

As if a thousand stackoverflow moderators and mentors cursed in unison and fell forever quiet.

Re: The user is visibly frustrated

#159

Post by contrast »

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…

"Teach yourself to not judge people for being human."

"Be a more charitable, generous, understanding person."

Anyone making such blatantly judgemental and egotistical comments to a complete stranger has absolutely no idea what is frustrating to people. And is not being anything like a charitable or understanding person.

Re: The user is visibly frustrated

#160

Post by gcr »

Arguing with the agent is an anti-pattern IMO.

When Claude acts up, my strategy is to rewind the conversation to the point where the misunderstanding started, revise what I said just before, and then continue from there. I’ve found that letting one mistake enter the conversation seems to make further mistakes more likely.

The user already has omnipotent power over the agent’s sense of time and memory. We can rewrite what Claude sees and hears. Can’t do that with humans, but rewinding such an important function in Claude that it has a top-level keystroke.

Why spend time, tokens, and cortisol arguing and demanding the pet rock step through an apology protocol?

Post reply on HN