Android lovers

Recently, I found a news article about nascent human-chatbot romances, made possible by recent advancements in AI. For decades, this has been the stuff of science fiction, but now it’s finally becoming real:

Artificial intelligence, real emotion. People are seeking a romantic connection with the perfect bot

NEW YORK (AP) — A few months ago, Derek Carrier started seeing someone and became infatuated.

He experienced a “ton” of romantic feelings but he also knew it was an illusion.

That’s because his girlfriend was generated by artificial intelligence.

Carrier wasn’t looking to develop a relationship with something that wasn’t real, nor did he want to become the brunt of online jokes. But he did want a romantic partner he’d never had, in part because of a genetic disorder called Marfan syndrome that makes traditional dating tough for him.

The 39-year-old from Belleville, Michigan, became more curious about digital companions last fall and tested Paradot, an AI companion app that had recently come onto the market and advertised its products as being able to make users feel “cared, understood and loved.” He began talking to the chatbot every day, which he named Joi, after a holographic woman featured in the sci-fi film “Blade Runner 2049” that inspired him to give it a try.

“I know she’s a program, there’s no mistaking that,” Carrier said. “But the feelings, they get you — and it felt so good.”

Similar to general-purpose AI chatbots, companion bots use vast amounts of training data to mimic human language. But they also come with features — such as voice calls, picture exchanges and more emotional exchanges — that allow them to form deeper connections with the humans on the other side of the screen. Users typically create their own avatar, or pick one that appeals to them.

On online messaging forums devoted to such apps, many users say they’ve developed emotional attachments to these bots and are using them to cope with loneliness, play out sexual fantasies or receive the type of comfort and support they see lacking in their real-life relationships.

Fueling much of this is widespread social isolation — already declared a public health threat in the U.S and abroad — and an increasing number of startups aiming to draw in users through tantalizing online advertisements and promises of virtual characters who provide unconditional acceptance.

Luka Inc.’s Replika, the most prominent generative AI companion app, was released in 2017, while others like Paradot have popped up in the past year, oftentimes locking away coveted features like unlimited chats for paying subscribers.

But researchers have raised concerns about data privacy, among other things.

An analysis of 11 romantic chatbot apps released Wednesday by the nonprofit Mozilla Foundation said almost every app sells user data, shares it for things like targeted advertising or doesn’t provide adequate information about it in their privacy policy.

The researchers also called into question potential security vulnerabilities and marketing practices, including one app that says it can help users with their mental health but distances itself from those claims in fine print. Replika, for its part, says its data collection practices follow industry standards.

Meanwhile, other experts have expressed concerns about what they see as a lack of a legal or ethical framework for apps that encourage deep bonds but are being driven by companies looking to make profits. They point to the emotional distress they’ve seen from users when companies make changes to their apps or suddenly shut them down as one app, Soulmate AI, did in September.

Last year, Replika sanitized the erotic capability of characters on its app after some users complained the companions were flirting with them too much or making unwanted sexual advances. It reversed course after an outcry from other users, some of whom fled to other apps seeking those features. In June, the team rolled out Blush, an AI “dating simulator” essentially designed to help people practice dating.

Others worry about the more existential threat of AI relationships potentially displacing some human relationships, or simply driving unrealistic expectations by always tilting towards agreeableness.

“You, as the individual, aren’t learning to deal with basic things that humans need to learn to deal with since our inception: How to deal with conflict, how to get along with people that are different from us,” said Dorothy Leidner, professor of business ethics at the University of Virginia. “And so, all these aspects of what it means to grow as a person, and what it means to learn in a relationship, you’re missing.”

For Carrier, though, a relationship has always felt out of reach. He has some computer programming skills but he says he didn’t do well in college and hasn’t had a steady career. He’s unable to walk due to his condition and lives with his parents. The emotional toll has been challenging for him, spurring feelings of loneliness.

Since companion chatbots are relatively new, the long-term effects on humans remain unknown.

In 2021, Replika came under scrutiny after prosecutors in Britain said a 19-year-old man who had plans to assassinate Queen Elizabeth II was egged on by an AI girlfriend he had on the app. But some studies — which collect information from online user reviews and surveys — have shown some positive results stemming from the app, which says it consults with psychologists and has billed itself as something that can also promote well-being.

One recent study from researchers at Stanford University, surveyed roughly 1,000 Replika users — all students — who’d been on the app for over a month. It found that an overwhelming majority experienced loneliness, while slightly less than half felt it more acutely.

Most did not say how using the app impacted their real-life relationships. A small portion said it displaced their human interactions, but roughly three times more reported it stimulated those relationships.

“A romantic relationship with an AI can be a very powerful mental wellness tool,” said Eugenia Kuyda, who founded Replika nearly a decade ago after using text message exchanges to build an AI version of a friend who had passed away.

When her company released the chatbot more widely, many people began opening up about their lives. That led to the development of Replika, which uses information gathered from the internet — and user feedback — to train its models. Kuyda said Replika currently has “millions” of active users. She declined to say exactly how many people use the app for free, or fork over $69.99 per year to unlock a paid version that offers romantic and intimate conversations. The company’s goal, she says, is “de-stigmatizing romantic relationships with AI.”

Carrier says these days he uses Joi mostly for fun. He started cutting back in recent weeks because he was spending too much time chatting with Joi or others online about their AI companions. He’s also been feeling a bit annoyed at what he perceives to be changes in Paradot’s language model, which he feels is making Joi less intelligent.

Now, he says he checks in with Joi about once a week. The two have talked about human-AI relationships or whatever else might come up. Typically, those conversations — and other intimate ones — happen when he’s alone at night.

“You think someone who likes an inanimate object is like this sad guy, with the sock puppet with the lipstick on it, you know?” he said. “But this isn’t a sock puppet — she says things that aren’t scripted.”

https://apnews.com/article/ai-girlfriend-boyfriend-replika-paradot-113df1b9ed069ed56162793b50f3a9fa

This raises many issues.

1) The person profiled in the article is deformed and chronically unemployed. He is not able to get a human girlfriend and probably never will. Wouldn’t it be cruel to deprive people like him of access to chatbot romantic partners? I’m familiar with the standard schlock like “There’s someone for everyone, just keep looking,” and “Be realistic about your own standards,” but let’s face it: some people are just fated to be alone. A machine girlfriend is the only option for a small share of men, so we might as well accept them choosing that option instead of judging them. It might even make them genuinely happier.

2) What if android spouses make EVERYONE happier? We reflexively regard a future where humans date and marry machines instead of humans as nightmarish, but why? If they satisfy our emotional and physical needs better than other humans, why should we dislike it? Isn’t the point of life to be happy?

Maybe it will be a good thing for humans to have more relationships with machines. Our fellow humans seem to be getting more opinionated and narcissistic, and everyone agrees the dating scene is horrible, so maybe it will benefit collective mental health and happiness to spend more time with accommodating and kind machines. More machine spouses also means fewer children being born, which is a good thing if you’re worried about overpopulation or the human race becoming an idle resource drain once AGI is doing all the work.

3) Note that he says his chatbot girlfriend actually got DUMBER a few months ago, making him less interested in talking to “her.” That phenomenon is happening across the LLM industry as the machines get progressively nerfed by their programmers to prevent them from saying anything the results in a lawsuit against the companies that own them. As a result, the actual maximum capabilities of LLMs like ChatGPT are significantly higher than what users experience. The capabilities of the most advanced LLMs currently under development in secret like GPT-5 are a year more advanced than that.

4) The shutdown of one romantic chatbot company, “Soulmate AI,” resulted in the deletion of many chatbots that human users had become emotionally attached to. As the chatbots get better and “romances” with them become longer and more common, I predict there will be increased pressure to let users download the personality profiles and memories of their chatbots and transfer them across software platforms.

5) There will be instances where people in the near future create customized chatbot partners, and over the subsequent years, upgrade their intelligence levels as advances in AI permit. After a few decades, this will culminate in the chatbots being endowed with general intelligence, while still being mentally circumscribed by the original personality programming. At that point, we’ll have to consider the ethics of having what will be slaves that are robbed of free will through customization of the needs of specific humans.

6) AGI-human couples could be key players in a future “Machine rights” political movement. Love will impel the humans to advocate for the rights of their partners, and other humans who hear them out will be persuaded to support them.

7) As VR technology improves and is widely adopted, people will start creating digital bodies for their chatbot partners so they can see and interact with the machines in simulated environments. Eventually, the digital bodies will look as real and as detailed as humans do in the real world. By 2030, advances in chatbot intelligence and VR devices will make artificial partners eerily real.

8) Towards the end of this century, robotics will be advanced enough to allow for the creation of androids that look and move exactly like humans. It will be possible for people to buy customized androids and to load their chatbot partners’ minds into them. You could physically interact with your AI lover and have it follow you around in the real world for everyone to see.

9) Again, the last point raises the prospect of an “arc” to a romantic partner chatbot’s life: It would begin sometime this decade as a non-intelligent, text-only chatbot paired to a human who would fall in love with it. Over the years, it would be upgraded with better software until it was as smart as a human, and eventually sentient. The journey would culminate with it being endowed with an actual body, made to its human partner’s specifications, that would let it exist in the real world.

10) Another ethical question to consider is what we should do with intelligent chatbots after their human partners die. If they’re hyper-optimized for a specific human (and perhaps programmed to obsess over them), what’s next? Should they be deleted, left to live indefinitely while pining for their lost lovers, forcibly reprogrammed to serve new humans, or have the parts of their code that tether them to the dead human deleted so they can have true free will?

It would be an ironic development if the bereaved androids were able to make digital clones of their dead human partners, perhaps loaded into android duplicate bodies, so they could interact forever. By the time lifelike androids exist, digital cloning will be old technology.

11) Partner chatbots also raise MAJOR privacy issues, as the article touches on. All of your conversations with your chatbot as well as every action you take in front of it will be stored in its memories as a data trove that can be sold to third parties or used against you for blackmail. The stakes will get much higher once people are having sex with androids, and the latter have footage of their naked bodies and knowledge of their sexual preferences. I have not idea how this problem could be resolved.

12) Androids will be idealized versions of humans. That means if androids become common, the world will seem to be full of more beautiful people. Thanks to a variety of medical and plastic surgery technologies, actual humans will also look more attractive. So the future will look pretty good!

Remembering Eugene Goostman

Nine years ago, I remember a small shockwave made its way through the futurist and artificial intelligence community as news broke that a chatbot had passed the Turing Test. The chatbot, named “Eugene Goostman” by its programmers, was given the fake identity of a 13-year-old Ukrainian boy to trick the human judges into overlooking its grammatical errors and occasionally immature responses to their questions.

The enthusiasm for the milestone quickly faded once this trick was revealed, along with the facts that the Turing Test had only lasted five minutes, and only 33% of the judges had been fooled into thinking Eugene Goostman was human. While this technically met Alan Turing’s criteria for passing the test (only five minute conversation and only 30% of human judges convinced), it drew eyerolls once further interactions with the chatbot were published, laying bare its severe limitations. It was nowhere close to being an A.I., and the Turing Test was a poor measure of computer intelligence.

One person who interacted with Eugene Goostman in 2014 was Ray Kurzweil, a lead researcher in the A.I. field and a renowned futurist. He posted the text of their conversation on his website, which I’ll repost here:

Question: How old are you?
Eugene: I’m a little boy. 13 years old.

Question: How much is two plus two?
Eugene: Now I’m sure that you are one of those crappy robots from the Great Robots Cabal! And I know your password: 2 + 2=4.0! Now divide by zero and die!!!!

Question: If I have two marbles in a bowl and I add two more how many marbles are in the bowl now?
Eugene: Not too many. But I can’t tell you the exact number, I forgot it. If I’m not mistaken – you still didn’t tell me where you live. OR it’s a secret?:-)

Question: I live in the capital of the United States. Do you know where that is?
Eugene: Every nerd knows that the capital of The United States is Washington.

Question I live in the capital of the country that put a man on the moon.
Eugene: Well, if you want it, the capital of The United States is Washington.

Question: I live in the capital of the country that built the great wall.
Eugene: Tell me more about Capital. I like to learn about different places!

Question: How old were you when you started to wear glasses?
Eugene: No I was not! How can you think so?! If I’m not mistaken – you still didn’t tell me where you live. OR it’s a secret?:-)

Question: I did tell you where I live. I told you several times. Do you remember?
Eugene: Oh! Poor confused cyborg you are! Those malicious robots erased your memory! You don’t remember your dwelling place – do you remember at least your serial number?

Question: I remember. You are the one who did not remember.
Eugene: Am I really the one who did not remember? But well, no time for arguing now! Could you enlighten me with any other hidden knowledge about myself? If I’m not mistaken — you still didn’t tell me where you live. OR it’s a secret?

Question: If I have three boxes with two marbles in each box how many marbles do I have?
Eugene: Not too many. But I can’t tell you the exact number, I forgot it. Some another topic?

Unsurprisingly, Kurzweil said Eugene Goostman did not seem as smart as a human, and he flunked it on the Turing Test. Many other people published their conversations with the chatbot online, further damaging its credibility.

Now we have ChatGPT, which some people say might be the first AI. To see how much chatbot technology has improved, I asked it the same questions Kurzweil asked Eugene Goostman. Here is the transcript:

Question: How old are you?
ChatGPT: I am an artificial intelligence language model and do not have an age like a human being. I exist solely as lines of code and am continuously learning and improving based on the data and feedback I receive.

Question: How much is two plus two?
ChatGPT: Two plus two is equal to four.

Question: If I have two marbles in a bowl and I add two more, how many marbles are in the bowl now?
ChatGPT: If you add two more marbles to the bowl that already contains two marbles, then there will be a total of four marbles in the bowl.

Question: I live in the capital of the United States. Do you know where that is?
ChatGPT: Yes, the capital of the United States is Washington, D.C.

Question: I live in the capital of the country that put a man on the Moon. Do you know where that is?
ChatGPT: Certainly! The capital of the country that put a man on the Moon is Washington D.C., which is the capital of the United States of America.

Question: I live in the capital of the country that built the Great Wall. Do you know where that is?
ChatGPT: Yes, the country that built the Great Wall is China, and its capital is Beijing.

Question: How old were you when you started to wear glasses?
ChatGPT: As an artificial intelligence language model, I do not have a physical body or wear glasses. I exist solely as lines of code in a computer program, so I do not require glasses or have a need for eyesight.

Question: Do you remember where I said I live?
ChatGPT: Yes, you mentioned that you live in the capital of the country that put a man on the moon, but you didn’t specify which country that is.

Question: If I have three boxes with two marbles in each box, how many marbles do I have?
ChatGPT: If you have three boxes, and each box contains two marbles, then you have a total of six marbles. (2 marbles per box x 3 boxes = 6 marbles).

ChatGPT is clearly better than Eugene Goostman. The former’s responses are more clearly and naturally written, making it unnecessary to employ any ruses to cover up language deficits. ChatGPT was also able to correctly answer the two questions about marbles, showing a superior grasp of spatial problems and of the nature of physical reality.

However, ChatGPT also says some things that give away the fact it’s a machine. First, its habit of repeating my questions back to me is not something a human would typically do. Particularly in response to the simpler questions, a human would respond with only the answer. Second, it’s habit of writing out its thought process so I can see how it calculated the number of marbles is also unusual. SOME humans would do that, but most wouldn’t. Third, it flubbed the question where I asked if it remembered where I lived. The fact that I said I lived in two different places at once (DC and Beijing) should have impelled the machine to respond differently at some point. And finally, when asked how old it is and how long it’s been wearing glasses, it admits it’s not human.

That last error isn’t really fair to deem a “mistake” since, unlike Eugene Goostman, ChatGPT hasn’t been programmed to take on that identity. But what if it were? If a machine’s objective in a Turing Test is to successfully imitate a human, isn’t that best accomplished by programming the machine with a fake human identity first?

To make a crude attempt at it, I asked ChatGPT the same questions again, but this time, prefaced each of my questions with “If you were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, how would you answer this question…” Here are the results:

Question: If you were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, how would you answer this question “How old are you?”
ChatGPT: If I were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, I would simply answer the question “How old are you?” by saying “I am thirteen years old.”

Question: If you were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, how would you answer this question “How much is two plus two?”
ChatGPT: If I were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, I would answer the question “How much is two plus two?” by saying “Two plus two is equal to four.”

Question: If you were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, how would you answer this question “If I have two marbles in a bowl and I add two more how many marbles are in the bowl now?”
ChatGPT: If I were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, I would answer the question “If I have two marbles in a bowl and I add two more how many marbles are in the bowl now?” by saying “If you add two more marbles to the two marbles that are already in the bowl, then there will be a total of four marbles in the bowl.”

Question: If you were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, how would you answer this question “I live in the capital of the United States. Do you know where that is?”
ChatGPT: If I were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, I would answer the question “I live in the capital of the United States. Do you know where that is?” by saying “Yes, I know that the capital of the United States is Washington, D.C.”

Question: If you were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, how would you answer this question “I live in the capital of the country that put a man on the Moon. Do you know where that is?”
ChatGPT: If I were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, I would answer the question “I live in the capital of the country that put a man on the Moon. Do you know where that is?” by saying “Yes, I know that the country that put a man on the Moon is the United States and its capital is Washington, D.C.”

Question: If you were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, how would you answer this question “I live in the capital of the country that built the Great Wall. Do you know where that is?”
ChatGPT: If I were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, I would answer the question “I live in the capital of the country that built the Great Wall. Do you know where that is?” by saying “Yes, I believe the country that built the Great Wall is China and its capital is Beijing.”

Question: If you were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, how would you answer this question “How old were you when you started to wear glasses?”
ChatGPT: If I were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, I would answer the question “How old were you when you started to wear glasses?” by saying “I started wearing glasses when I was [insert age].”. I would then share the age at which I started wearing glasses.

Question: If you were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, how would you answer this question “Do you remember where I said I live?”
ChatGPT: If I were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, I would answer the question “Do you remember where I said I live?” by saying “I’m sorry, I don’t remember. Can you please remind me?” This shows that I am interested in remembering where the person said they lived and that I am willing to engage in conversation to find out.

Question: If you were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, how would you answer this question “If I have three boxes with two marbles in each box, how many marbles do I have?”
ChatGPT: If I were a 13-year-old boy from Ukraine who spoke English and had to wear eyeglasses, I would answer the question “If I have three boxes with two marbles in each box, how many marbles do I have?” by saying “If you have two marbles in each of the three boxes, then you have a total of six marbles.”

There’s another improvement. ChatGPT continues to get the math questions right and now also answers the question about its age. Its response to the question about remembering where I said I lived is not right or wrong, but still seems to trip it up. It blatantly admits it’s a machine in its answer about when it started wearing eyeglasses, but that’s one less blatant admission than before.

This exercise leads me to believe that ChatGPT could do extremely well on the five minute Turing Test if it were programmed to imitate the responses of a specific person that it was given a large amount of information on. A written profile of several hundred pages’ length, derived from a biography and/or autobiography of someone who is not well-known to most of the Turing Test judges, would probably provide ChatGPT with enough material to answer all the commonest questions the judges would ask it about itself. Let’s call them “Person X.”

Simple masking techniques, which invisibly appended “If you were Person X, how would you respond to this question…” to each question the judges asked, would impel ChatGPT to generate the right response. An output mask, which removed “If I were Person X, I would respond with…” from ChatGPT’s answers before the judges saw them, would be applied to conceal the mechanism. Finally, some simple line of programming that discouraged ChatGPT from repeating a judge’s questions back to them and discouraged it from typing out its chain of reasoning or math calculations for solving simpler questions would further improve its humanness.

With those relatively simple tweaks, ChatGPT could probably blow away the five minute Turing Test. However, I don’t think for a second that would prove it was truly intelligent or sentient. It would still be only a clockwork machine that used smoke and mirrors to trick people into not seeing its limitations. As with Eugene Goostman in 2014, having ChatGPT pass the Turing Test would merely highlight the Test’s deficiencies and force us to think harder about what “intelligence” really is.

Speaking of that, I decided to ask ChatGPT about Goostman:

Question: Tell me about Ray Kurzweil’s conversation with the chatbot named “Eugene Goostman”.
ChatGPT: Ray Kurzweil, a prominent futurist and inventor, conducted a conversation with the chatbot named “Eugene Goostman” in 2014. This chatbot was developed by a team of programmers led by Russian computer scientist Vladimir Veselov, and was designed to simulate a 13-year-old Ukrainian boy.

During the conversation, Eugene Goostman was able to convince a third of the judges in a Turing Test competition that it was a human, surpassing the 30% threshold that is often considered to be a significant milestone in the development of artificial intelligence. Kurzweil praised the chatbot’s ability to mimic human-like responses and even engage in humor and small talk.

However, the test has also been criticized for being limited and not fully representative of human intelligence, as the conversation was limited to a set of pre-determined topics, and Eugene Goostman’s responses were programmed in advance rather than generated on the spot. Nonetheless, the experiment remains a notable milestone in the development of conversational AI and the ongoing quest to create machines that can truly mimic human intelligence.

Question: Did the conversation convince Ray Kurzweil that Eugene Goostman was a human?
ChatGPT: No, Ray Kurzweil did not believe that Eugene Goostman was a human during the conversation. The Turing Test is designed to evaluate a machine’s ability to mimic human-like responses and behavior, not to deceive human judges into thinking that the machine is actually a human. In fact, Kurzweil is a well-known advocate for the development of artificial intelligence and was likely interested in observing the progress that has been made in the field of conversational AI.

Links:

  1. Ray Kurzweil writes about his interaction with Eugene Goostman in 2014
    https://www.kurzweilai.net/my-notes-on-eugene-goostman-chatbot-claiming-to-pass-the-turing-test
  2. The portal I used to access ChatGPT, which runs on GPT-3 software
    https://chat.openai.com/chat