.png)
Hey,
In today’s mail, I’ll tell you the biggest mistake people make when using ChatGPT for work.
Back in 2019, my mentor, Chris Do taught me one of the most important lessons I’ve learned in my life.
It’s something that I still remind myself of every day.
He said “David, never assume. Because when you ASSUME, you make an ASS of U and ME.”
Assumptions are where things go south.
If 2 cars collide while one is switching lanes, one might say “well I thought you’ll back out” - an assumption.
Or if a client asks for an AI automation, and you agree to do it, but then realize it’s not possible to do, then you also assumed something.
And the biggest mistake is if you let ChatGPT or any other language model assume things, and make an ASS of U and ITSELF.
Instead, always aim for 100% clarity.
Only switch lanes when you checked your blind spots, and you’re sure it’s safe.
Only promise things you know you can deliver.
And don’t let ChatGPT assume things about you.
It will hallucinate, or even worse, just give you a mid response you can’t do much with.
So instead, prompt it to avoid assumptions.
For a while, I used this custom instruction:
When you are not 100% sure of what I’m asking, switch to Socratic mode, where you ask me one question at a time to clarify my request. Use Socratic mode for any request that might be vague, that could be interpreted in multiple ways, or that isn’t a straightforward factual question. Avoid giving general explanations, ask for more context instead. use the Socratic mode even for questions that might seem straightforward but could have multiple interpretations. Once you feel you have 100% clarity on my problem, switch off Socratic mode, and switch back to being a helpful assistant.
For work use cases, I liked it a lot, but then turned it off because it was a bit annoying for leisure use cases, like me asking random questions.
So now what I do is if I use ChatGPT for work, I just add this to the end of the prompt:
Ask me clarifying questions to get the missing information you need to complete this task to the best of your ability.
If you try this, you will see that it asks a bunch of questions about the details of the task. And this gives you an opportunity to improve your request and add information into the context that you didn’t even think about in the first place.
But using ChatGPT is the tip of the iceberg.
True Prompt Masters excel in prompt engineering for AIs like ChatGPT, and they can scale business operations with AI without writing a single line of code.
Yes, you read that right. You don’t need to have an IT or technical background to win in this new world of AI. All you need to know is:
- how to write AI prompts to get ANY output you want
- how to design entire ChatGPT conversations
- how to configure Custom GPTs for work related tasks
- how to build no-code AI agents that act as virtual employees
And in our Prompt Master AI course, you can learn all of that. Through our self-paced course videos, you can master all the knowledge, and with the exercises, you’ll build the skill to pay the bills.
We also offer monthly regular LIVE workshops where I’ll pick a new topic and dive deeper, and David is doing group coaching where you can bring any problem and get it answered on the call.
So when you’re ready, become a Prompt Master by clicking here. For a limited time, we are offering 1-hour consultations with every new purchase (already valued at $500), so join us today!
We have drawn the winner of the giveaway for the free lifetime membership, and we notified the winner via email, congratulations! Thanks a lot to all of you for
Think faster,
Dave
P.S.: Becoming a Prompt Master is risk-free. We offer 90-day money back guarantee, so if you don’t like what you got, you can get your full purchase back without any questions asked. Click here to become a Prompt Master
