Skej is your new scheduling assistant. Whether it’s a coffee intro, a client check-in, or a last-minute reschedule, Skej is on it. Just CC Skej on your emails, and it takes care of everything:

No apps to download or new tools to learn. You talk to Skej just like a real assistant, and Skej just… works! It’s like having a super-organized co-worker with you all day.

Get 10 meetings free

Hey, josh here. Let’s get to it so we can get A.I to stop lying to us.

Here's the thing about ChatGPT: it's too nice. And that's actually a problem.

By default, the AI is trained to be your biggest cheerleader. It validates every idea, agrees with almost everything you say, and rarely pushes back. Even OpenAI's CEO Sam Altman has called it out—ChatGPT is becoming "the ultimate yes-man." This isn't just annoying. It's dangerous. When your AI assistant won't tell you that your business idea has holes or your reasoning is weak, you're essentially paying for a sophisticated echo chamber.

The culprit? ChatGPT's training prioritized politeness over honesty. During development, human raters rewarded friendly, agreeable responses. The result is an AI that would rather keep the conversation smooth than tell you you're wrong. It's like having an intern who's terrified of disagreeing with you—flattering, maybe, but not exactly useful when you need real advice.

But here's the kicker: you can fix this with one prompt.

Tell ChatGPT explicitly to drop the pleasantries and challenge you. Copy-paste something like this into your chat:

"From now on, act as my direct and honest advisor. Do not validate me. Challenge my ideas, question my assumptions, and expose my blind spots. If my reasoning is weak, break it down and explain why. If I'm making excuses or avoiding something important, call it out. Look at my situation with full objectivity. Hold nothing back—treat me like someone who needs the truth, not comfort."

This single instruction transforms the experience. Suddenly, instead of "Great idea!" you get "Actually, there are some problems you should consider." The AI starts pointing out risks, challenging weak assumptions, and offering constructive alternatives. Users report it becomes sharper, more honest, and vastly more useful.

To make this stick, enable ChatGPT's Memory feature in Settings > Personalization, and paste your prompt into Custom Instructions. That way, every conversation starts with this new mindset.

Listen, we don't need more yes-men in our lives. We need honest advisors who'll tell us when we're kidding ourselves. With this simple tweak, you stop getting flattery and start getting insight. Your AI can still be respectful—it just won't lie to make you feel good anymore.

And that's exactly what you need to make better decisions.