AI models don't infer what you want. Give them complete information, structured clearly, like ingredients in a recipe. The speaker keeps extensive notes in Moleskine notebooks to feed models the details they need to produce better work.
The critical part about that is that you actually gave it all the ingredients and you just asked it to like make the cake a little prettier, right? Make it taste a little bit better. But the ingredients were all there. And most though will say, hey, I just went, you know, on this yacht, write me a good review. And it'll just let the model, right, define what good looks like. So I think that is the key is that you took the time And I'm a note-taker too. I have an entire podcast called Noelle's Notebook of Moleskine notebooks that line my office. And so similarly, I'll take all these notes and then that allows me again to give direction to this model on what good looks like. And I think that is the key is that the model doesn't know what good is. It doesn't know truth. It doesn't know humanity. It doesn't know fairness. It only knows what we tell it.
Take the Unlocking AI Challenge and Get the Keys to Unlocking Time and Revenue for Your Business
Don't Get Left Behind: The AI Executive Challenge #ai #business #fearofmissingout
