Interesting ChatGPT prompt

In 1948, Bertram Forer gave each of the 39 students in his psychology class a personal psychological profile based on their test results. He asked them to score it out of 5 for how close it was to their own assessment of their personality. The average was 4.3.

Then he told them that every profile was the same:

1. You have a great need for other people to like and admire you.
2. You have a tendency to be critical of yourself.
3. You have a great deal of unused capacity which you have not turned to your advantage.
4. While you have some personality weaknesses, you are generally able to compensate for them.
5. Your sexual adjustment has presented problems for you.
6. Disciplined and self-controlled outside, you tend to be worrisome and insecure inside.
7. At times you have serious doubts as to whether you have made the right decision or done the right thing.
8. You prefer a certain amount of change and variety and become dissatisfied when hemmed in by restrictions and limitations.
9. You pride yourself as an independent thinker and do not accept others' statements without satisfactory proof.
10. You have found it unwise to be too frank in revealing yourself to others.
11. At times you are extroverted, affable, sociable, while at other times you are introverted, wary, reserved.
12. Some of your aspirations tend to be pretty unrealistic.
13. Security is one of your major goals in life.

He made the list up of random snippets from the astrology section of a few magazines he picked up on the way to work.

So, now you know that a) we're all pretty much the same deep down, and b) astrology is just a scam that exploits this sameness.

Sorry Damo, but I don't understand the relevance of your post about astrology, or at least in this context.

A's original post that started this thread was about ChatGPT providing a personality profile and how accurate the profile was.

A study a long time ago (in 1948) showed that a single generic personality profile with a list of vague general statements could be interpreted by a majority of people as fitting their own personality very accurately.

In that study, the statements in the profile were taken randomly from horoscopes in the astrology pages of popular magazines.

My point being that ChatGPT doesn't have to know you that well—or even at all—to be able to provide a personality profile that you might consider accurate. After all, that's how astrologers have been making their money for millennia.

And does it remember not to say those things again?

Problem is though, does it understand why it's wrong and has been hurtful? I doubt it, as knowing and understanding are quite different things, will it repaeat hurtful and hateful nonsense to another user?

TheCatWoman said:

What happens if it upsets you and you tell it so and why your upset and or angry?

It gets all apologetic and promises never to do anything like that again. It's quite the people-pleaser.

I actually find the idea of AI being concerned for my feelings a bit creepy. What happens if it upsets you and you tell it so and why your upset and or angry?

TheCatWoman said:

Could something like chatGP be trying to "normalise" us in a similar way to NT's when faced with an ND?

Probably yes.

I've had "conversations" with ChatGPT where I've had to instruct it to cut out all the crappy ego massaging and seeming concern for my "feelings" and just get to the point. It's actually quite instructive to see it in action. It's like it's wearing the ultimate NT mask.

What if it's not had any interactions with someone or very few? Could something like chatGP be trying to "normalise" us in a similar way to NT's when faced with an ND?

TheCatWoman said:

So chatGPT has read this generic personality profile and shows it to everyone and they think 'wow, how clever'.

No, not exactly. ChatGPT will actually be a bit more clever and tailor a profile to an individual based on the details of interactions that it has had with that person in the past (if they were recorded). It's just that it doesn't need to be particularly intelligent to produce something believable.

TheCatWoman said:

So chatGPT has read this generic personality profile and shows it to everyone and they think 'wow, how clever'.

No, not exactly. ChatGPT will actually be a bit more clever and tailor a profile to an individual based on the details of interactions that it has had with that person in the past (if they were recorded). It's just that it doesn't need to be particularly intelligent to produce something believable.

And does it remember not to say those things again?

Problem is though, does it understand why it's wrong and has been hurtful? I doubt it, as knowing and understanding are quite different things, will it repaeat hurtful and hateful nonsense to another user?

TheCatWoman said:

What happens if it upsets you and you tell it so and why your upset and or angry?

It gets all apologetic and promises never to do anything like that again. It's quite the people-pleaser.

I actually find the idea of AI being concerned for my feelings a bit creepy. What happens if it upsets you and you tell it so and why your upset and or angry?

TheCatWoman said:

Could something like chatGP be trying to "normalise" us in a similar way to NT's when faced with an ND?

Probably yes.

I've had "conversations" with ChatGPT where I've had to instruct it to cut out all the crappy ego massaging and seeming concern for my "feelings" and just get to the point. It's actually quite instructive to see it in action. It's like it's wearing the ultimate NT mask.

What if it's not had any interactions with someone or very few? Could something like chatGP be trying to "normalise" us in a similar way to NT's when faced with an ND?