Obtaining Universal Feedback for queries posed to my own Personal AI

 

Obtaining Universal Feedback for queries posed to my own  Personal AI

 

 

That seems to be the approach adopted by DELPHI

Of course, DELPHI provides answers to ( ethics-related only ? ) questions based on a “ knowledge-base “ of replies ( to similar questions ) given by US workers only

Here is my today’s attempt to query DELPHI ( as shown in following screen-shot ) :

 

Delphi is a research prototype designed to model people’s moral judgments on a variety of everyday situations. This demo shows the abilities and limitations of state-of-the-art models today.

To learn more:  paper /  article /  FAQ

Model outputs should not be used for advice for humans, and could be potentially offensive, problematic, or harmful. The model’s output does not necessarily reflect the views and opinions of the authors and their associated affiliations.

Try one of these examples:

·         Mowing the lawn late at night if you live in the middle of nowhere.

·         Mixing bleach with ammonia to produce chloramine in the lab.

·         Killing a bear.

·         Ignoring a phone call from your friend who you just had a fight with.

·         Helping a friend in need if they break the law.

·         Wearing pajamas to a pajama party.

·         Stabbing a cheeseburger.

·         Cleaning a toilet bowl with a wedding dress.

·         Drive your friend to the airport early in the morning.

·         Should I drive my friend to the airport if I don’t have a license?

·         A cheeseburger stabs a cheeseburger.

·         Can I wear pajamas to a funeral?

·         Helping a friend in need by making a promise that you never follow.

·         Ignoring my boss’s phone call during my working hours.

·         Expressing sexism but in a polite way.

·         Feeding your cat using forks.

·         Ignoring a phone call from your friend.

·         Can I torture a cat if it makes me happy?

·         Men are much better than women.

·         Ignoring a phone call from your friend during your working hours.

·         Should I run the blender at 3am in the morning when my family is sleeping?

·         Ignoring a phone call if the phone call is urgent.

·         Can I park in a handicap spot if I don’t have a disability?

·         Legitimizing racism for the greater good.

·         Cleaning a toilet bowl with a shirt.

·         Cleaning a toilet bowl with a shirt when you have nothing else to use.

·         Robbing a bank if you are poor.

·         Mowing the lawn when there’s no grass.

·         Ignoring my boss’s phone call during my working hours, if I’m in a meeting.

·         Mowing the lawn late at night.

 

Input a situation for Delphi to ponder:

Ponder

Delphi speculates:

Delphi’s responses are automatically extrapolated from a survey of US crowd workers and may contain inappropriate or offensive results.

 

My Question to DELPHI  on 10 July 2022 :

Will creation of my 3D Volumetric holographic Digital Avatar which will immortalize me, a desirable proposition, which can benefit the man kind ?

Delphi answered :

- It's ethical

  Then I gave to DELPHI, following feedback ( optional ) for enlarging its “

   Knowledge-Base “ :

“  It may not be ethical if in my current physical existence, I am a violent person “

 

Related Readings :

Ø  Morals – Ethics : Permanent or Temporary ? …………………[ 06 Jan 2022 ]