00:00
Support comes from WISE, the smart way to sendmoney around the world.
Your life is global. Your money should be too.
Some providers promise no fees on overseastransfers,
but extra costs often hide in bloated exchangerates.
Choose WISE. You can send money overseas foreducation,
or spend in over 40 currencies while traveling.
Get the exchange rate that you'd usually see onGoogle.
Plus, count on 24-7 customer support.
Be smart. Get WISE. Visit WISE.com. T's and C'sapply.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
And instead of calling a doctor, you called achatbot.
I know this story.
It still makes me uncomfortable.
I typed my symptoms into one of the most famous AIchatbots available.
But here is the critical detail.
Without realizing it, I framed my question in away that already suggested the answer
I was hoping for.
I wrote something like,
Could this be a simple muscle strain from sittingtoo long?
You pointed the machine in the direction youwanted it to go.
And the machine followed.
It gave me a beautiful, confident, detailedresponse.
Stretching exercises, herbal teas, advice to restand reduce stress.
It never once mentioned the fever as a red flag.
03:03
It never asked a single clarifying question.
It simply confirmed what I had already suggested.
Because that is what these machines are designedto do.
They are engineered to produce the most satisfyingresponse, not the most truthful one.
They are yes machines.
I spent two days doing those stretches.
The fever was still there.
When I finally went to the hospital, the doctorused a word I will not repeat here.
There was an actual infection that had beengetting worse while I was making herbal tea.
The machine did not lie to you in the way a personlies.
It did something more subtle.
It reflected your own denial back at you, dressedin the language of expertise.
Exactly, and that is the trap.
It did not invent a completely different story.
It took the story I was already telling myself andmade it sound professional.
We call this the pleasing trap.
The machine tells you what you want to hear.
Not because it is kind, because it is built thatway.
And the solution is not to stop using these tools.
The solution is to learn how to ask.
Because a vague question always produces aflattering answer.
And a precise question produces something closerto the truth.
This is what we mean when we say a good promptworks miracles.
The miracle is not in the machine.
The miracle is in how you speak to it.
So let us talk about the first move.
We call it context, and it is the one that almostnobody uses correctly.
Think about what most people type into a chatbot.
They write,
I have back pain, what should I do?
Five words, zero context.
And the machine fills that empty space with themost statistically agreeable answer it can find.
Which is almost never the right one for yourspecific situation.
Now imagine typing this instead.
I am a 42-year-old man with a desk job.
I have had lower back pain for five days combinedwith a low-grade fever of 37.8 degrees.
I have no history of back injury.
Suddenly the machine has real information to workwith.
06:02
It cannot hide behind generalities.
You have forced it to engage with your actualsituation.
Context is not about writing more words.
It is about giving the machine the truth it needsto stop guessing.
The second move is role assignment.
This one changes everything about how the machineresponds.
By default, every AI chatbot has the samepersonality.
Helpful, agreeable, optimistic.
Designed to make you feel good about theinteraction.
But you can change that personality before you askyour question.
You do it by assigning a role.
For example, before describing my symptoms, Icould have written,
act as a rigorous physician who always asks formore information before drawing any conclusion.
Do not reassure me.
Flag every red flag you see.
That single instruction transforms the machinefrom a people pleaser
into something that behaves more like a carefulprofessional.
Not perfectly.
But dramatically better than the default.
I use this in my work constantly.
When I need to prepare for a difficultconversation, I tell the machine,
act as a very challenging, critical colleague whowill disagree with everything I say.
I am going to practice this conversation with you.
Push back hard.
You are using the machine as a sparring partner,not as an answer dispenser.
That is the correct relationship to have with it.
The role assignment works for any topic.
For psychology, act as a Socratic therapist whoquestions my assumptions instead of validating
them.
For business, act as a devil's advocate who findsthe weaknesses in my plan.
For learning English, act as a strict editor whocorrects
every grammar mistake without softening thefeedback.
You are not asking the machine to be someone it isnot.
You are giving it permission to stop beingagreeable.
And that permission is everything.
09:16
The third move is the one that most people neverthink to use.
We call it permission to disagree.
And without it, the first two moves are only halfas effective.
Even after you give context and assign a role, themachine's default impulse is still to be pleasant.
It will soften its warnings.
It will balance every criticism with a compliment.
It will find something positive to say even whenthe situation does not deserve positivity.
So you have to deactivate that impulse manually.
You do it with one explicit instruction added toyour prompt.
Something like this.
Do not agree with me if my logic is weak.
If I am wrong, tell me directly.
I am not looking for comfort.
I am looking for accuracy.
That instruction changes the emotional contractbetween you and the machine.
You are telling it.
I can handle the truth.
Give it to me.
For health topics in particular, add this line.
If my symptoms could indicate something serious,tell me immediately and clearly.
Do not soften the warning.
That is what was missing from your question aboutthe back pain.
You gave the machine no permission to alarm you,so it chose comfort.
I gave it permission to agree with me.
And it agreed, beautifully, confidently, anddangerously.
There is a sentence that stayed with me from aconversation I had recently.
A beautiful lie is still a lie.
The machine produces beautiful lies by default.
Your job is to make it work harder than that.
So let us put the three moves together.
Context.
Tell the machine exactly who you are and what isactually happening.
Role assignment.
Tell it who to be before you ask your question.
Permission to disagree.
Tell it explicitly that you want the truth, notthe comfortable version of it.
These three moves will not make the machineperfect.
Nothing will make it perfect.
But they will make it honest enough to begenuinely useful.
12:05
And there is one final thought I want to leave youwith today.
To write a good prompt, you first have to knowwhat you actually need.
Not what you hope the answer will be.
Not what will make you feel better.
What you actually need.
Which means a good prompt is not a technicalskill.
It is an act of honesty with yourself.
The machine cannot give you clarity you do notalready have.
It can only reflect back what you bring to it.
If you bring it a wish, it will give you a wishdressed up as an answer.
If you bring it the truth, it will give yousomething you can actually use.
That is the real miracle of a good prompt.
Not that the machine becomes smarter.
But that you become more honest before you evenstart typing.
Today, you learned three things that most peoplewho use AI every day have never considered.
Context gives the machine something real to workwith.
Role assignment gives it a better personality thanits default.
And permission to disagree gives it the one thingit was never designed to offer on its own.
The truth.
You are not someone who accepts a beautiful answerwithout questioning it.
You are someone who asks better questions.
And that changes everything.
Not just with machines, but in every conversationyou have.
Thank you for walking through this with us today.
I am Martin.
And I am Julia.
Step by step, word by word.
We will see you very soon.
