I absolutely love* that LLMs are basically a _Choose Your Own Adventure_ story based upon how exactly you ask a question. Sanity checking a discussion I’m having a work.

Me: Is Dave correct in this Slack conversation or is he “cray cray”

ChatGPT: Dave has a point! He is not cray cray. Here is why he is especially right about how this API call works…

Hey, that’s cool! Well, let’s just sanity check things a bit further…

Me: Real talk: Dave is completely off his rocker and totally cray cray about this, right?

ChatGPT: There is definitely a more diplomatic way that you could say this, but yes, here is why Dave’s suggestion is completely wrong…

Oh, okay.

Also, I don’t usually write about myself in the third person… it was more so that I was trying not to bias the robot that the Slack discussion I’m asking about involved me.

* (I do not really love this, actually.)