AI works best when you treat it like an idiot.
A little context: I co-host a small NFL player prop show as a side project. Since I am apparently incapable of enjoying hobbies like a normal person, I expanded my existing research to create an AI research system to augment my own analysis. I want to know the ball on camera, obviously.
It started simply: analyzing the games. Find interesting accessories for gamers. Tell me what you think. Let’s make some money!
That worked surprisingly well, until it didn’t.
Welcome to another edition of Prompt Mode, your weekly AI newsletter.
I’m PCWorld Executive Editor Brad Chacos, filling in this week for your host, Ben Patterson. Every week in Quick modeWe’ll offer analysis of AI trends that matter to everyday users like you and me. Stay tuned for practical AI tips, hands-on experiences with the latest AI tools, and, you guessed it, pointers to help you get the most out of your AI assistants.
Thanks for reading, and if you like what you see, just register here.
AI desperately wants to be useful. Ask him a question and he’ll want to give you an answer, even when the correct answer is “I don’t know.” Give him a theory and he will happily find evidence to support it. Find a promising new approach and if you’re not careful, suddenly that approach has somehow become part of the methodology that supposedly produced last month’s results. I could go on.
So BWR, as I call my increasingly deranged side project, evolved. And when I saw how stupid and forgetful AI can be, I started putting it in a cage.
