You're not wrong but also there's a ton of misinformation out there, both due to bad journalism and also pro-LLM advocates, that is selling the idea that LLMs are actually real AI that is able to think and reason and is operating within ethical boundaries of some kind.
Neither of those things are true but that's what a lot of available information about LLMs would have you believe so it's not difficult to imagine someone engaging with a chatbot ending up with a similar result without trying to force it explicitly via prompt engineering.
You're not wrong but also there's a ton of misinformation out there, both due to bad journalism and also pro-LLM advocates, that is selling the idea that LLMs are actually real AI that is able to think and reason and is operating within ethical boundaries of some kind.
Neither of those things are true but that's what a lot of available information about LLMs would have you believe so it's not difficult to imagine someone engaging with a chatbot ending up with a similar result without trying to force it explicitly via prompt engineering.