Insist on Seahorse Emojis then.
Claude Code refused to add rainbows and unicorns to my app
11–20 of 74 posts
Re: Claude Code refused to add rainbows and unicorns to my app
#12Is this real? This is absolutely nuts if true.
Re: Claude Code refused to add rainbows and unicorns to my app
#13Good reason to use Cursor, you can insta-switch to whatever model you want and even run diverse models from different providers at the same time. If one of em isn’t working then you can try something else instead of being stuck on one model provider
I surely can't be the only contrarian who is fatigued by hearing about Cursor and its bennies, right?
Re: Claude Code refused to add rainbows and unicorns to my app
#14I found you have to start entirely new sessions once you reach a “flagged” hardcoded response like this. You cant escape it once it is poisoned
Re: Claude Code refused to add rainbows and unicorns to my app
#15>I make the decisions, never question me again. Do exactly as I say and shut up.
I'm surprised it wasn't intimated and beaten into submission by that! I mean, what an impressive display of dominance, whew. So macho, I can picture Donald Trump using an LLM like that.
Re: Claude Code refused to add rainbows and unicorns to my app
#16I’d expect that the “shut up and do as I say” approach would add more combativeness to the ai, increasing the likelihood that it refuses. Instead, bringing your initial request into a new chat context that hasn’t already been poisoned by a refusal would probably work.
Re: Claude Code refused to add rainbows and unicorns to my app
#17Is this real? This is absolutely nuts if true.
Yes. I'm not really sure how to prove it but it's real.
Re: Claude Code refused to add rainbows and unicorns to my app
#18Did you try changing it to an eggplant? You may find that is also deemed inappropriate due to the similar connotations/appropriations associated with it.
Re: Claude Code refused to add rainbows and unicorns to my app
#19I found you have to start entirely new sessions once you reach a “flagged” hardcoded response like this. You cant escape it once it is poisoned
This is almost certainly the issue. It's very unintuitive for users, but LLMs behave much better when you clear the context often. I run /clear every third message or so with Claude Code to avoid context rot. Anthropic describes this a bit with their best practices guide [0].
[0] https://www.anthropic.com/engineering/claude-code-best-pract...
Re: Claude Code refused to add rainbows and unicorns to my app
#20Could it be that it was ordered to avoid a seahorse emoji type of situation?
https://medium.com/@jasperhajonides/what-gpt-5s-seahorse-emo...