an AI model that runs as an LLM also spits out a number from 0-100 representing how certain it is that the data it’s giving is accurate. 

Surely at least of the current models can identify queries that might make them prone to hallucinations? Right? 

Gemini seems to just speak with such certainty when I search on google but is often just flat out wrong and verifiably so by just scrolling to the top results below the AI summary. So weird to me that it presents all its answers with equal confidence

Hi, I’m Jack.🤷‍♂️ chronically unserious, cautiously cynical. @crybabygoblin is my gf.                          

Customer/User Experience Specialist/Consultant

Oh yeah. I’ve had some hallucinations. 

Why I find it so ironic a program created with logic and math can’t do math. 

And then when you tell it. They like. Oh yeah. Your right. 

Bitch. You should know! You’re the AI! 🤖

I see that being plausible but I’m talking about when Googles AI summary is just wrong for no good reason. For example it told me yesterday that there were four locations in my state of a restaurant that has no locations here in reality

If it seems like an important simple solution. The only logical conclusion is it is on purpose ? 

Like sponsored top posts. Hmmm. 

GIGO world. And it’s garbage all the way down.

I imagine it's impossible for an AI model to fact check its own output because they can't read and digest their own output.