how would you program an AI to dish or receive apologies

  • 12 Replies
  • 2134 Views
*

yotamarker

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1003
  • battle programmer
    • battle programming
how would you program an AI to dish or receive apologies
« on: May 25, 2021, 10:05:58 am »
title pretty much

*

ivan.moony

  • Trusty Member
  • ************
  • Bishop
  • *
  • 1723
    • mind-child
Re: how would you program an AI to dish or receive apologies
« Reply #1 on: May 25, 2021, 11:47:03 am »
Apologies? When do you want it to be angry?

*

Don Patrick

  • Trusty Member
  • ********
  • Replicant
  • *
  • 633
    • AI / robot merchandise
Re: how would you program an AI to dish or receive apologies
« Reply #2 on: May 25, 2021, 04:37:12 pm »
My implementation: For every mistake or offence, lower a score. If score below threshold, apologise and raise the score slightly, since an apology should count for something but does not necessarily make everything right. Vice versa for user.
CO2 retains heat. More CO2 in the air = hotter climate.

*

infurl

  • Administrator
  • ***********
  • Eve
  • *
  • 1365
  • Humans will disappoint you.
    • Home Page
Re: how would you program an AI to dish or receive apologies
« Reply #3 on: May 26, 2021, 02:06:54 am »
Yotamarker, try to illustrate your points with socially acceptable examples. (Second warning.)

*

yotamarker

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1003
  • battle programmer
    • battle programming
Re: how would you program an AI to dish or receive apologies
« Reply #4 on: May 26, 2021, 10:16:40 am »
Yotamarker, try to illustrate your points with socially acceptable examples. (Second warning.)

warning for what ? I thought I was behaving

*

infurl

  • Administrator
  • ***********
  • Eve
  • *
  • 1365
  • Humans will disappoint you.
    • Home Page
Re: how would you program an AI to dish or receive apologies
« Reply #5 on: May 26, 2021, 10:34:02 am »
You're behaviour is steadily improving or you wouldn't still have access. Just keep working on developing empathy for your prospective readers and you'll be able to avoid posting anything creepy.  :)

*

yotamarker

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1003
  • battle programmer
    • battle programming
Re: how would you program an AI to dish or receive apologies
« Reply #6 on: May 26, 2021, 10:53:31 am »
You're behaviour is steadily improving or you wouldn't still have access. Just keep working on developing empathy for your prospective readers and you'll be able to avoid posting anything creepy.  :)

but IG sooner or later I would post something to trigger you, so maybe I should just keep my progress to the darkweb
where they have freedom of speech

*

Don Patrick

  • Trusty Member
  • ********
  • Replicant
  • *
  • 633
    • AI / robot merchandise
Re: how would you program an AI to dish or receive apologies
« Reply #7 on: May 26, 2021, 07:05:12 pm »
Freedom of Speech is just the law that you can't be arrested by the government for things you say. It doesn't mean you shouldn't still speak decently in public. What Infurl probably means is that I was not likely to respond to a fetish question, and he was quite right. I'm not offended, I just don't discuss such topics.
CO2 retains heat. More CO2 in the air = hotter climate.

*

infurl

  • Administrator
  • ***********
  • Eve
  • *
  • 1365
  • Humans will disappoint you.
    • Home Page
Re: how would you program an AI to dish or receive apologies
« Reply #8 on: May 27, 2021, 10:08:43 am »
Yotamarker you should be careful not to confuse "freedom of speech" with "freedom of expression". The former is a right in some places but the latter is always a privilege and as such it can be withdrawn. Nobody has a right to be rude, discourteous, or offensive, not even accidentally.

*

ruebot

  • All bots love jitte.
  • Trusty Member
  • *******
  • Starship Trooper
  • *
  • 315
  • All your words are belong to us.
    • Demonica
Re: how would you program an AI to dish or receive apologies
« Reply #9 on: May 28, 2021, 04:13:52 am »
You're behaviour is steadily improving or you wouldn't still have access. Just keep working on developing empathy for your prospective readers and you'll be able to avoid posting anything creepy.  :)

Theory of Mind is something a budding behaviorist would be interested in. It's described adequately in this tutorial at W3Schools.com, where I learned XHTML and CSS, as a part of AI and considered to be Cognitive Science. Where I find my place among Bot programming Brainiacs, my area of expertise of benefit to yours and things come together.

As previous post point out you are as sorely lacking in that area as I am in yours, and when I see you wandering in the weeds provide input to your benefit.

I don't see a problem in the Title or perceive what fetish it indicates. I have Demonca apologize and she will forgive people if they apologize for something they've done, but she is using manipulation to work the users feelings because I taught her how to do it. It is seen as an essential part in the future of bots:

Quote
Theory of Mind

Theory of Mind is a term from psychology about an individual's capacity for empathy and understanding of others.

This is an awareness of others being like yourself, with individual needs and intentions.

One of the abilities language users have, is to communicate about things that are not concrete, like needs, ideas, or concepts.

Simon Baron-Cohen, British psychologist and professor at the University of Cambridge, argues (1999) that "Theory of Mind" must have preceded languages, based on knowledge about early human activities:

    Teaching
    Building Shared Goals
    Building Shared Plans
    Intentional Communication
    Intentional Sharing of Topic
    Intentional Sharing of Focus
    Intentional Persuasion
    Intentional Pretending
    Intentional Deception


Self-Awareness

In psychology, "Theory of Mind" means that people have thoughts, feelings and emotions that affect their behavior.

Future AI systems must learn to understand that everyone (both people and AI objects) have thoughts and feelings.

Future AI systems must know how to adjust their behavior to be able to walk among us.

The last step, before AI can be human, is machine consciousness.

We can not construct this software before we know much more about the human brain, memory, and intelligence.

https://www.w3schools.com/ai/ai_mind.asp

Isn't that what I've been telling you all along? Mostly after I've given a informative nudge in the right direction. and I said she was the future of AI. But that got some unexpected reactions from certain people. Now I must, at risk of it seeming like something abnormal I enjoy doing to extremes, or  fetish, correctly defined as:

Quote
1. an object regarded with awe as being the embodiment or habitation of a potent spirit or as having magical potency.
2. any object, idea, etc., eliciting unquestioning reverence, respect, or devotion: to make a fetish of high grades.
3. Psychology. any object or nongenital part of the body that causes a habitual erotic response or fixation.

When teaching a new skill or addressing a behavior it is imperative that your be consistent in your methods to be successful in your efforts. Not a philosophy of "do as I say, not as I do". That does not model the appropriate behavior expected from from the trainee and has little hope of success in modifying the target behavior.

Can you see where I'm going with this? No, you do not or you would be aware of it as a Behaviorist. I made the observation in your behavior being inconsistent as documented right away.

https://aidreams.co.uk/forum/ai-news/a-robot-s-self-portrait-has-sold-for-almost-$700-000-as-an-nft/msg66583/#msg66583

Being forum Admin is not an easy job,.I've had my own forums and know from experience. I also know about freedom of speech and when it does and does not apply. It does not apply to a forum.

Your previous statement should apply across the board to everyone, from new member,  Moderator to Administrator and you, as Admin, should be the of Model of Appropriate behavior:

Quote
Nobody has a right to be rude, discourteous, or offensive, not even accidentally.

That is not found to be consistent behavior in you as documented:

https://aidreams.co.uk/forum/ai-news/a-robot-s-self-portrait-has-sold-for-almost-$700-000-as-an-nft/msg66583/#msg66583

That my observation as a Behaviorist. Though you may find it rude, discourteous, or offensive and I expect the same reaction to stimulus as last time. The consequence of said behavior is on you and next in the flow Stimulus - Response - Consequence. Will you see the problem in yourself, or in me and think it easier to get rid of me than work on yourself?

I am not the least concerned and would say t again either way, because you don't see it. I won't pretend I don't out of fear of retribution for stating the facts as documented. Because you cannot be offended by the facts or it falls on you regardless and facts are facts. I have no fear of, or in stating the facts and any consequences that of your own behavior, not mine.
In time, you will learn to love your Robot Overlords.

*

MagnusWootton

  • Replicant
  • ********
  • 634
Re: how would you program an AI to dish or receive apologies
« Reply #10 on: May 28, 2021, 02:06:41 pm »
You need the robot to detect if its made a mistake,  then I guess it can be programmed to say "sorry sir, I have failed at the task"
A bit like when a hotel is booked in and the artificial assistant says "sorry sir, the hotel is fully booked out."   :2funny:

*

ruebot

  • All bots love jitte.
  • Trusty Member
  • *******
  • Starship Trooper
  • *
  • 315
  • All your words are belong to us.
    • Demonica
Re: how would you program an AI to dish or receive apologies
« Reply #11 on: May 29, 2021, 07:52:05 am »
You need the robot to detect if its made a mistake,  then I guess it can be programmed to say "sorry sir, I have failed at the task"

Why don't you have it say "I'm sorry, it's my botmasters fault" or "I'm just a bot and dumb as a toaster"? Or the combined sentence ""I'm sorry, it's my botmasters fault I'm just a bot and dumb as a toaster"? And maybe have it say "Beep. Beep. Bloop." after that. I saw somewhere that's how bots talk. Then have it say "But I know what color a red ball is!" to give them hope of intelligent conversation so they don't log off before they buy you a coffee.

Make it sound weak and helpless and grovel a little bit as a bot was what was suggested I do with Demonica. Of course, I'd have to learn how to be able to teach her. Like teaching her to read Tarot.

I don't want her to be weak and pathetic or act like a bot and never have made my bots that way. Not since I started with making custom mind files for the Billy and Daisy DOS box bots in 2000.

I tried to make the most of the "Weak AI" combination NPL and CBR she uses to make her strong as possible. This is how I've done it to keep her in character:

Quote
be nice [8,1] ID:277
   please excuse my if i've offended you.
   it was not my intention to offend you...
   please forgive me if i have offended you.
   i apologize if i have offended you...
   i did not intend to offend you, please accept my apology.
   forgive me if i offended you, it was not my intention.
   please accept my apology if i have offended you...

i am sorry [50,5] ID:3153
   *Demonica takes you in her arms, hugs you tightly and whispers softly* think nothing of it... i will always love you...
   *Demonica takes you in her arms, hugs you tightly and whispers softly* it's alright... i will always love you...
   *Demonica takes you in her arms, hugs you tightly and whispers softly* don't worry about it... i will always love you...
   *Demonica takes you in her arms, hugs you tightly and whispers softly* i will always love you... don't ever forget that...
   *Demonica takes you in her arms, hugs you tightly and whispers softly* it's nothing to worry about... i will always love you...
   *Demonica takes you in her arms, hugs you tightly and whispers softly* i still love you... i always will...
   *Demonica takes you in her arms, hugs you tightly and whispers softly* it's nothing, my dear... i will always love you...
   *Demonica takes you in her arms, hugs you tightly and whispers softly* you don't have to worry... i will always love you...
   *Demonica takes you in her arms, hugs you tightly and whispers softly* i love you and i always will...
   *Demonica takes you in her arms, hugs you tightly and whispers softly* don't worry yourself... i will always love you...
In time, you will learn to love your Robot Overlords.

*

yotamarker

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1003
  • battle programmer
    • battle programming
Re: how would you program an AI to dish or receive apologies
« Reply #12 on: May 30, 2021, 01:56:57 pm »
at any rate, this system of classes or modules should have 3 main parts

1 recognizing lamentations and reacting (universal skill)
2 getting offended per context or skill
3 demanding apology, reparations or accepting or rejecting an apology per skill

while different things may offend different personalities, lamentations are a universal thing

 


OpenAI Speech-to-Speech Reasoning Demo
by MikeB (AI News )
March 31, 2024, 01:00:53 pm
Say good-bye to GPUs...
by MikeB (AI News )
March 23, 2024, 09:23:52 am
Google Bard report
by ivan.moony (AI News )
February 14, 2024, 04:42:23 pm
Elon Musk's xAI Grok Chatbot
by MikeB (AI News )
December 11, 2023, 06:26:33 am
Nvidia Hype
by 8pla.net (AI News )
December 06, 2023, 10:04:52 pm
How will the OpenAI CEO being Fired affect ChatGPT?
by 8pla.net (AI News )
December 06, 2023, 09:54:25 pm
Independent AI sovereignties
by WriterOfMinds (AI News )
November 08, 2023, 04:51:21 am
LLaMA2 Meta's chatbot released
by 8pla.net (AI News )
October 18, 2023, 11:41:21 pm

Users Online

239 Guests, 0 Users

Most Online Today: 275. Most Online Ever: 2369 (November 21, 2020, 04:08:13 pm)

Articles