alt Hacker NewsI'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 helped kick it out of a glut and onto the right track.
Or it could just be catharsis.
Replies
I would prefer not having to get into a habit that might bleed into non-LLM interactions.
As if a thousand stackoverflow moderators and mentors cursed in unison and fell forever quiet.
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.
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.
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.
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/
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.)
I don't understand - are people's agents making so many mistakes? I'm using VSCode + Cline + Mimo to refactor big codebases and add features (including payment integrations) and it's rarely making any mistakes.
Whenever I throw slurs at them they just refuse to respond
I just say "bruh". Per knowyourmeme:
> "Bruh" is a popular variant of the slang term "bro" that is often used as an interjection to convey frustration or disappointment at something.
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.
I've found a mix of peppered in upper case words where you are effectively yelling at the LLM also gives it a strong signal. It is also a bit cathartic.
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.