From my experience, LLMs understand prompt just fine, even if there are substantial typos or severe grammatical errors.

I feel that prompting them with poor language will make them respond more casually. That might be confirmation bias on my end, but research does show that prompt language affects LLM behavior, even if the prompt message doesn't change/

And in "soul.md" no less! Imagine having a soul full of grammatical errors. No wonder that bot was angry.

Probably led the LLM to dial up the "hubris" setting to 11