Comment by wouldbecouldbe

8 hours ago

I dont know what really happened here. Maybe his curse word did prompt a block, maybe something else caused the block.

But to be honest I've been cursing a lot to Claude Code, im migrating a website from WordPress to NextJS. And regardless of my instructions I copy paste every prompt I send it keeps not listening and assuming css classes & simpliying HTML structure. But when I curse it actually listens, I think cursing is actually a useful tool in interacting with LLM's.

3 comments

wouldbecouldbe

Reply
another_twist  8 hours ago

Use caps. DO NOT DO X. works like a charm on codex.

  • ssl-3  7 hours ago

    From my own observations with OpenAI's bots, it seems like there's nuanced levels.

    "Don't do that" is one level. It's weak, but it is directive. It often gets ignored.

    "DON'T DO THAT" is another. It may have stronger impact, but it's not much better -- the enhanced capitalization probably tokenizes about the same as the previous mixed-case command, and seems to get about the same result. It can feel good to HAMMER THAT OUT when frustrated, but the caps don't really seem to add much value even though our intent may for it to be interpreted as very deliberate shouting.

    "Don't do that, fuckface" is another. The addition of an emphatic and profane quip of an insult seems to generally improve compliance, and produce less occurrence of the undesired behavior. No extra caps required.