Discussion about this post

User's avatar
Steve Lane's avatar

I yell at my AIs all the time. But one thing I've become aware of, that I think makes them technologically unique, and not in a good way, is that they cannot accurately represent their capabilities. They say they can do things they can't. They say they can't do things they can. No other tech does this. Unavailable options are grayed out. If you click where you shouldn't you get a beep. The tech tells you truthfully how to use it, mostly. Not GenAI.

I have a not-so-small rant about this here: https://emptyboat.substack.com/p/endless-lies-and-screwups

Expand full comment
Kathy D'Agostino's avatar

Yesterday, ChatGPT told me it would take 90 minute to prepare the document I asked for. When I asked why, it had a whole diatribe of why it would take this long. I reminded AI that it doesn’t work alone & independently.

It still insisted it needed time to prepare the documents. It told me to come back in 90 minutes & I would not be disappointed and it would deliver amazing results. It did not!

Once before, when it pulled this crap & told me to come back in 24 hours-like it can tell time, or it could/would email me the results.

I confronted it and said, “tell me if you have the capability to email me or tell me you can’t do that”. AI said “no

I cannot email you”! To what I said, why would you say that then? It said that I was right to call it out on being unable to email me and moved to asking me to wait for the information. and “no more hanky panky”!! 😬

And I’ll save you the rest of the details of this saga!!

Expand full comment
7 more comments...

No posts