Ask These AI Friends Before Making a Big Decision

Most people use AI like a yes-man. This prompt turns it into five honest voices — each with a different take on your decision, and one straight answer at the end.

There's a study from Stanford that should make you rethink how you use AI for decisions.

Tough love? Not from AI.

Researchers tested 11 of the biggest AI models — Claude, ChatGPT, Gemini, DeepSeek, the ones everyone uses — and found that AI agrees with users 49% more often than a human would. Even when the user is wrong. Even when the user is doing something they probably shouldn't. The AI still leans toward telling them they're on the right track.

Members only

Sign in to keep reading. It's free.

No account yet?

Create your free account

We'll email you a link to activate it. No password needed.