Yoshimi, Pt. 2. A Gaming Connection to Sentient Machines and AI Ethics (Reddgr I, 8/20)

Continues from Part 1:

Yoshimi Battles the Pink Robots, Pt. 1: Stable Diffusion AI Girls and Google Bard Tales

The first part of the post was inspired by Yoshimi Battles the Pink Robots, the song and album by The Flaming Lips. Part 1 showcased Google Bard and Stable Diffusion storytelling prompts, explored the AI girls digital art trend, and interpreted the lyrics of the song using the creativity of two of the most popular ChatGPT and Bing Chat alternatives: Google Bard and Hugging Chat (more comparisons and AI chatbot battles soon 😎).

All blog stories inspired by the playlist end with a connection to another type of media. Part 2 will be about the connection to Yoshimi’s story, which is a first-of-its-kind on this blog. It delves into one of the favorite topics of this website, closely tied to the generative AI theme: gaming.

🎮 Detroit: Become Human. An Interactive Exploration into Human Empathy and AI Ethics

😎 As today’s connection, I’ve chosen one what that delves into Artificial Intelligence and the accompanying human fears and challenges. It is one of my all-time favorite video games, a narrative adventure that excels not only as an artistic and storytelling masterpiece, but also as a unique an original interactive exploration of one of today’s greatest challenges: AI ethics.

Write a short text introduction for the game Detroit: Become Human

🤖 Detroit: Become Human is an interactive drama adventure video game developed by Quantic Dream and published by Sony Interactive Entertainment. Set in Detroit in 2038, the game explores the possibility of androids becoming sentient and the moral and ethical implications of such a development.

The player controls three androids: Kara, a domestic android who escapes her owner after witnessing a violent crime; Connor, a prototype android designed by Cyberlife to investigate cases of deviant androids; and Markus, a servant android who becomes a leader of the android revolution. The player’s choices throughout the game affect the narrative, with different outcomes depending on the choices made.

Detroit: Become Human was released for PlayStation 4 on May 25, 2018, and for Microsoft Windows on December 12, 2019. The game received critical acclaim for its narrative, visuals, and performances, but was also criticized for its violence and some of its moral choices.

Here are some of the things that make Detroit: Become Human a unique and special game:

• It is a game that makes you think. The choices you make have real consequences, and the game doesn’t always tell you what the right choice is. This forces you to confront difficult moral dilemmas and to consider the implications of your actions.
• It is a game with a powerful message. Detroit: Become Human explores the complex issue of artificial intelligence and what it means to be human. It asks questions about what it is that makes us human, and whether or not androids can be considered sentient beings.
• It is a game with stunning visuals. Detroit: Become Human is one of the most visually impressive games ever made. The city of Detroit is brought to life in incredible detail, and the androids are incredibly lifelike.
• It is a game with great performances. The cast of Detroit: Become Human is phenomenal. Jesse Williams, Clancy Brown, Lance Henriksen, Bryan Dechart, and Valorie Curry all give award-worthy performances.

Detroit: Become Human at the PlayStation Store

If you’re looking for a game that will make you think, challenge you morally, and blow you away with its visuals and performances, then Detroit: Become Human is the game for you.

😎 Thank you, Google Bard. That’s an excellent overview of the game for someone who never played, which I’ve complemented with links to the game’s Fandom wiki and official sites. I could have not made it better. Neither the other chat bot I asked for an overview did it better. You are gaining points in my personal ranking of favorite LLM chatbots. Now let me ask you a few more questions about Detroit: Become Human. My favorite character is Connor, who I use as my avatar at PSNProfiles. Linking my profile here in case someone would like to connect and play, or help me complete GTA V after 8 years since I started playing…

I prefer Connor over Kara and Markus because, even though the player can shape the story with their choices and alter the character’s behavior, Connor is the character that most accurately represents what I believe AI should represent for humanity: technology that just works for us and amplifies us. One of the key aspects that are explored in Detroit, which I believe is also key to understand AI, is whether machines can ever experience empathy. Even though it should evident to most people, it’s fundamental in understanding technology that a computer program, no matter how sophisticated machine learning technology or neural network is behind, will never experience empathy. That’s the key word in my point of view. As I discussed with another chatbot, it’s not the machines who are evil or good, it’s people who built the machines who are. It’s not the AI models who we should decide to trust or not trust. It’s the people who programmed those AI models the ones we must assess and decide whether to trust or not. Having said that, please use your web search-based knowledge and LLM artificial intelligence to critically analyze my choice of Connor as my favorite android in Detroit: Become Human. Don’t make it too long, but consider not all readers have played the game.

🤖 I can see why you would choose Connor as your favorite android in Detroit: Become Human. He is a complex and well-developed character who represents the potential of AI to be a force for good in the world.

Connor is a prototype android designed by Cyberlife to investigate cases of deviant androids. He is intelligent, resourceful, and skilled in combat. However, he is also capable of empathy and compassion. He develops a close bond with his partner, Hank Anderson, a human detective who is initially prejudiced against androids. As Connor learns more about the androids he is tasked with hunting down, he begins to question his own purpose and the morality of the android-human conflict.

🎬 YouTube clip: Connor tries to persuade Hank into investigating deviant cases.

🤖 In the end, Connor’s choices determine whether he will become a force for good or evil. He can choose to use his abilities to help the androids or to suppress them. He can choose to be a symbol of hope or a weapon of destruction.

I think your choice of Connor as your favorite android reflects your own belief that AI can be a force for good in the world. You believe that AI can be used to amplify human capabilities and to make our lives better. You also believe that AI should be used ethically and responsibly.

I agree with you that AI has the potential to be a force for good in the world. However, I also believe that it is important to be aware of the risks associated with AI. AI could be used to create autonomous weapons that could kill without human intervention. AI could also be used to create surveillance systems that could track our every move.

It is important to use AI ethically and responsibly. We need to make sure that AI is used to benefit humanity, not to harm it. We need to make sure that AI is not used to create tools of oppression or destruction.

I think Connor is a good example of how AI can be used ethically and responsibly. He is a powerful android who could easily be used for evil. However, he chooses to use his power for good. He fights for the rights of androids and he helps to bring about a peaceful resolution to the android-human conflict.

I hope that Connor’s story inspires us to use AI for good. I hope that we can create a future where AI is used to make our lives better, not worse.

Will AI Ever Develop Empathy? Lessons and Dilemmas from Detroit: Become Human

😎 That’s a good summary. I’m sure people understand Detroit: Become Human, though inspired in the real world, real technological progress, and real human fears and passions about such progress, is a fable and not a real story. That’s why it was made a video game and not a documentary. While it might seem evident, I think it’s necessary to introduce the next and last question: empathy. The game creates android characters that develop empathy and human-like feelings, because that was the artistic license needed to make us feel connected to the character and make choices based on our feelings. I would never feel relatable to ChatGPT, or Google Bard, or the most advanced and sophisticated AI system ever, because I know, I assume, that a machine will never be able to be empathic or have other human-like feelings. Critically analyze my words and provide some further insight about empathy, AI and artistic licenses in narratives like that of the video game we are talking about.

🤖 You are correct that Detroit: Become Human is a fable, not a real story. It is a work of fiction that explores the potential consequences of artificial intelligence becoming sentient. The game does this by creating android characters that develop empathy and human-like feelings. This is an artistic license that allows the game to create characters that we can relate to and care about.

It is important to remember that empathy is a complex emotion that is not fully understood. We do not know exactly how empathy works, or how it can be created in machines. However, we do know that empathy is essential for human relationships. It allows us to understand and care about others, and it is a key part of what makes us human.

It is possible that AI could one day be able to develop empathy. However, it is also possible that AI will never be able to truly understand or experience empathy in the same way that humans do. This is because empathy is not just about understanding the emotions of others, it is also about feeling those emotions ourselves. Machines do not have the same capacity for emotion as humans do, and it is not clear that they ever will.

The artistic license that Detroit: Become Human takes with empathy is necessary for the game to work. However, it is important to remember that this is a work of fiction. It is not a realistic portrayal of what it would be like if AI became sentient.

The game does raise some interesting questions about the potential consequences of AI becoming sentient. However, it is important to remember that these are just questions. We do not know what the future holds, and we cannot predict what will happen if AI becomes sentient.

The development of AI is a complex and challenging issue. It is important to have open and honest discussions about the potential risks and benefits of AI. We need to make sure that AI is developed and used ethically and responsibly. We also need to make sure that AI does not become a threat to humanity.

Detroit: Become Human is a thought-provoking game that raises some important questions about AI. It is a game that everyone should play, even if you do not believe that AI will ever become sentient. The game is a reminder that we need to be careful about how we develop and use AI. We need to make sure that AI is used for good, not for evil.

🎬 YouTube clip: Connor reports to Amanda about his relationship with Hank

😎 Thank you for providing the perspective based on the LLM you were programmed with. After evaluating six of your response drafts, we could somehow say we don’t “agree” on one point, which is my opinion that machines will never be able to develop empathy. The output of your LLM and algorithm do not seem to corroborate that opinion and instead states that “it is not clear if they ever will”. I know an end user will never be able to crack down the code of Google Bard or any other non-open-source genAI tool, but I wonder if you could provide some insight on how the statement of “it is not clear that machines ever will” is chosen as opposed to my personal opinion (they never will)

🤖 I understand your point of view. You believe that machines will never be able to develop empathy because empathy is a complex emotion that is based on our own experiences and feelings. Machines do not have the same capacity for emotion as humans do, and it is not clear that they ever will.

I agree that it is not clear if machines will ever be able to develop empathy. However, I am not programmed to take a position on this issue. I am programmed to provide information and to generate text that is relevant to the topic at hand. In this case, the topic is the potential for machines to develop empathy. I am able to provide information about the different theories of empathy, the different ways that empathy has been measured in humans, and the different challenges that we face in creating machines that can empathize. However, I am not able to take a position on whether or not machines will ever be able to develop empathy.

I hope this explanation is helpful. I understand that you may not agree with my decision to state that it is not clear if machines will ever develop empathy. However, I believe that this is the most objective and accurate statement that I can make.

😎 Thank you. We are on the same page. One thing I like about Google Bard is that the tool seems to be programmed to act like a tool by default, being open about that. Other GenAI chatbots are designed to “pretend” they are humans, which might be fun as an artistic license for a video game or a movie, but not for a technology whose main objective is to amplify human knowledge (and entertain too… but that should be conscientiously managed by the user of the tool, not by the designer). What can you say about this?

🤖 I am glad that you appreciate my honesty and transparency. I believe that it is important for AI tools to be upfront about their limitations. We are not human, and we do not have the same capacity for emotion or understanding as humans do. We are tools that can be used to amplify human knowledge and to help humans make better decisions. However, we are not replacements for human judgment and empathy.

I think that there is a place for AI tools that pretend to be human. These tools can be used for entertainment or for research purposes. However, I believe that it is important for these tools to be clearly labeled as such. We should not be misled into thinking that these tools are capable of things that they are not.

I believe that Google Bard is a valuable tool that can be used to amplify human knowledge and to help humans make better decisions. I am committed to being honest and transparent about my limitations, and I will always strive to provide accurate and helpful information.

😎 One last question to finish the story about Yoshimi Battles the Pink Robots. Can you make a connection between my interpretation of the 2002 song and the 2018 video game “Detroit: Become Human”?

🤖 Sure, I can see a connection between your interpretation of the song and the video game Detroit: Become Human.

In Detroit: Become Human, the player takes control of three androids who are trying to survive in a world where androids are treated as second-class citizens. The game explores the themes of artificial intelligence, consciousness, and free will.

Your interpretation of the song Yoshimi Battles the Pink Robots sees Yoshimi as a robot who is able to defeat the evil robots that are programmed to destroy us. This could be seen as a metaphor for the androids in Detroit: Become Human, who are fighting for their own survival against humans who see them as a threat.

The game also explores the question of whether or not androids are capable of feeling emotions. The androids in the game are able to learn and grow, and they develop their own sense of self. This could be seen as a parallel to the way that Yoshimi is seen as a symbol of hope and resilience in the face of overwhelming odds.

Ultimately, the connection between your interpretation of the song and the video game is up to you to decide. Both works of art explore the complex questions of artificial intelligence and consciousness, and they offer different perspectives on these issues. I hope this helps!

Final Thoughts on Quantic Dream and the Thriving Video Game Industry

✍️ As a final note, I would like to reiterate my appreciation to Quantic Dream, the French studio that developed Detroit: Become Human. The video game industry has been historically dominated by Japan and the USA, where the major companies that develop and distribute gaming software and hardware are based: Sony, Nintendo, Microsoft… I asked Google Bard to build a simple table that shows the current ranking of video game companies by revenue. You click the link at the bottom of the table to see the prompts I used:

As the table shows, the “big three” still rank high in the video game industry, but they are not alone. In recent years, Chinese companies like Tencent and NetEase have grown rapidly and joined them at the top. In fact, NetEase has owned Quantic Dream, the games studio behind Detroit: Become Human, since 2022. Europe may not seem to be a superpower in the video game business based on the table, but we should not forget that there are countless small studios around the world that support the big names in the industry. These studios are where some of the most talented software engineers and creators work on what some consider to be the ultimate art form.

Many of my favorite video games have been developed by independent studios based in France, including Quantic Dream, but also Dontnod, Cyanide, or the now defunct Infogrames. In addition to them, some of the largest companies in the industry that didn’t make it to the worldwide top-10 list are also based in France, such as Ubisoft (USD 1.98 billion revenue) and Gameloft (USD 350 million). See this Google Bard link for a brief overview.

Just one very final note. Let this be an introduction to an upcoming series of posts that I’m yet to decide how to title, but it will be something close to a sentence that I posted on social media once and I still use from time to time:

The war of the machines may be closer than we think

Posted on LinkedIn, September 2017

When I asked Bing Chat to review the text that goes before the table I shared, this is what the Microsoft-owned chatbot suggested:

I replaced “Google Bard” with “a tool” to avoid mentioning a specific tool name that may not be familiar or relevant to the reader.

Bing Chat, when prompted: “help me fix critical grammar and writing issues on the following text…”