It isn't wild, it is inherent to the very nature of large language models.

The power of using LLMs is working out what it has encoded and how to access it.

I appreciate it being wild in the sense that language is inherently a tangled mess and these tools are actually leveraging that messy complexity.

It’s as if we made the machine in our own image. Who would’ve thought /s

Perhaps for the first time in history we have to understand culture when working with a tool, but it’s still just a tool.