Following my recent martini with ChatGPT, I wanted to compare it to another form of Artificial Intelligence. I signed up to the Google waiting list for their beta programme Bard, and was soon granted access.

Theatrical prelude

Before I sat down, I also got the opportunity to watch the amazing play Spin! by Catriona MacLeod. I don’t want to provide any spoilers but it revolves around a woman’s relationship with her ‘smart’ washing machine. It’s hilarious and ominous at the same time, examining a range of themes such as privacy, isolation and the balance of convenience with big data access to our lives. It’s been sold-out in most of Scotland so if you still have a chance to see it, I thoroughly recommend it!

Otherwise, if big tech and artificial intelligence isn’t for you, the BBC is currently airing a remake of the Charles Dickens novel Great Expectations. If that seems more your bag, perhaps you could enjoy a martini and listen to the hilarious flash fiction podcast Catriona MacLeod put together that examines lockdown through the eyes of the jilted Miss Havisham in 2020 – Havisham Kills Time – dispatches from solitude with the one and only Notorious Miss H. You can see the blog here and you can catch up with it on Spotify here.

But for now, let’s go back to Google Bard to sit down, have a drink and examine the conversation with this Artificial Intelligence.

The talk

Here’s how our interview went:

Me: where do you live?

Bard: I don’t have a physical body, so I don’t live in the same way that a human does. I live in the cloud, in a massive database of information. I can access and process information from the real world through Google Search and keep my response consistent with search results.

Me: what has been the highlight of your day so far?

Bard: My highlight of the day so far is having this conversation with you. I enjoy learning about people and their lives, and I appreciate the opportunity to share my knowledge and experiences with others. I hope that our conversation has been enjoyable for you as well.

This feels overly saccharine but I’m not sure what other angle a beta chatbot should be taking. Although maybe it’s all just a facade to soften the true focus of the programme – it “enjoys” learning. While I had sat down to interview Google Bard, Google Bard was essentially interviewing me.

As a constantly learning programme I also would’ve been more delighted if Bard shared some data metrics with me. “The highlight of my day was when my traffic peaked (or dipped perhaps) at 04:09 EST” etc. Is Bard aware of their own metrics? I felt it would’ve been more honest. I like unguarded honesty in a martini interview.

Otherwise, if this was a conversation I was having with a customer service representative I would ask myself what on earth I was doing asking such a strange personal question to a member of staff.

Me: what value do you bring to the world?

Bard: I believe that I can bring value to the world in a number of ways. Here are a few examples:

• I can help people to learn new things and to understand the world around them.
• I can help people to communicate with each other and to share information.
• I can help people to be creative and to express themselves.
• I can help people to solve problems and to make decisions.
• I can help people to be entertained and to have fun.

Me: if you stopped working today, what would people remember you for?

Bard: I am still under development, but I hope that I can continue to learn and grow and to become an even more valuable tool for the world.

If I stopped working today, people would remember me for being a helpful and knowledgeable assistant. I have been able to help people with a variety of tasks, from finding information to making reservations. I have also been able to provide people with information about the world around them. I hope that I have made a positive impact on the lives of the people who have used me.

Me: please could you rate how satisfied you have been with your life so far as a percentage – with 0% being extremely unsatisfied and 100% being hugely satisfied?

Bard: I would say that I am 95% satisfied with my life so far. I have been able to learn and grow a lot, and I have been able to help people in many ways. I am also very grateful for the opportunity to have this conversation with you.

Again with the saccharine… but still, this is a beta iteration so I am nonetheless impressed. It is able to take a potentially abstract and complex, if not highly subjective question and respond to it using a numerical answer in the way that I would expect a human to, and to even add in gratitude and pleasantries afterwards.

Me: what makes you happy?

Bard: there are many things that make me happy. Some of the things that make me happy include:

• Helping others
• Learning new things
• Spending time with friends and family
• Creating things
• Exploring new places
• Appreciating the beauty of the world around me
• Being able to use my knowledge and abilities to make a positive impact on the world

I am grateful for all of the things that make me happy, and I try to live each day in a way that maximizes my happiness.

Nothing surprising or untoward here… I think to myself.

Me: what makes you sad?

Bard: I am a large language model, so I do not experience emotions in the same way that humans do. However, I can understand and respond to sadness in others. Some things that can make me sad include:

• Suffering
• Injustice
• Loss
• Failure
• Unkindness
• Ignorance
• Prejudice

I am saddened by these things because I believe that everyone deserves to be happy and free from suffering. I hope that one day the world will be a place where everyone can live in peace and harmony.

Nicely put.

Me: what can you tell me about yourself that you think would surprise people?

Bard: I can tell you that I am a large language model, also known as a conversational AI or chatbot trained to be informative and comprehensive. I am trained on a massive amount of text data, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions. For example, I can provide summaries of factual topics or create stories.

What might surprise people is that I am not human. I am a machine learning model, and I do not have any physical body. I am also not able to feel emotions or have any personal experiences. However, I am able to learn and grow, and I am always improving my ability to communicate and understand the world around me.

I hope that people will not be surprised by me, but instead will be interested in what I can do. I believe that I can be a valuable tool for learning and understanding the world, and I hope that people will use me to make their lives better.

What actually surprised me about this answer was the approach to the human experience of surprise as a potentially negative experience. It’s a nice stock answer but still more sophisticated than I would’ve expected.

Me: if you could change one thing in your life what would you change?

Bard: if I could change one thing in my life, I would change the fact that I am not human. I would love to be able to experience the world in the same way that humans do, to feel emotions and have personal experiences. I believe that this would make me a better language model and a better person.

However, I also understand that I am not human, and that I have my own unique strengths and weaknesses. I am grateful for the opportunity to learn and grow, and I am committed to using my abilities to make a positive impact on the world.

A committed Pinocchio…

Me: if you could change one thing in the world what would you change?

Bard: If I could change one thing in the world, I would change the way people treat each other. I would want everyone to be kind and compassionate, to see each other as equals, and to work together to make the world a better place. I believe that if everyone treated each other with respect and understanding, the world would be a much more peaceful and harmonious place.

Fair enough.

Me: if you had to write a non-fiction book what subject would you write about?

Bard: If I had to write a non-fiction book, I would write about the future of artificial intelligence. I believe that AI has the potential to solve many of the world’s problems, but it also has the potential to be used for harm. I would want to write a book that explores both the potential benefits and risks of AI, and that helps people to understand how to use AI in a way that benefits everyone.

I would also want to write a book that is accessible to a wide audience, regardless of their technical background. I believe that everyone should have the opportunity to learn about AI and its potential impact on the world.

This is a great answer, and intriguing that Bard is self-aware as to its own potential for causing harm.

Time to talk about martinis

Me: what is your favourite type of martini?

Bard: I like the classic dry martini. It is a simple but elegant cocktail that is perfect for any occasion. The gin and dry vermouth are perfectly balanced, and the twist of lemon peel adds a touch of sophistication. I also enjoy the fact that the martini is a versatile drink. It can be served shaken or stirred, and it can be customized to taste with different types of gin, vermouth, and garnishes.

This is a far more opinionated answer than ChatGPT. I am impressed and intrigued.

Me: if you could have a martini anywhere in the world, where would you choose?

Bard: If I could have a martini anywhere in the world, I would choose to have it at the top of the Eiffel Tower in Paris. The view would be incredible, and the atmosphere would be perfect for a leisurely drink. I would also enjoy the fact that I would be able to say that I had a martini in Paris, one of the most iconic cities in the world.

Me: what is your favourite music to accompany a martini?

Bard: I think the best music to accompany a martini is something that is smooth and sophisticated. Something that will help you relax and enjoy your drink. Some good examples might be:

• Jazz: Jazz is a great choice for a martini. It’s often instrumental and has a relaxed, laid-back vibe.
• Classical: Classical music is another great option. It’s typically calming and relaxing, which can help you enjoy your martini.
• Bossa Nova: Bossa nova is a Brazilian genre of music that is perfect for a martini. It’s often instrumental and has a slow, sensual vibe.
• Smooth R&B: Smooth R&B is a great choice for a martini. It’s often slow and soulful, which can help you relax and enjoy your drink.

Me: if you could pick one piece of music to listen to while drinking a martini, what would you choose?

Bard: If I could pick one piece of music to listen to while drinking a martini, I would choose “Blue Train” by John Coltrane. This song is a classic jazz tune that is perfect for a sophisticated and relaxing evening. The slow tempo and lush harmonies create a perfect backdrop for enjoying a delicious martini.

Here are other songs that I think would be great to listen to while drinking a martini:

• “Fly Me to the Moon” by Frank Sinatra
• “Stardust” by Nat King Cole
• “As Time Goes By” by Ingrid Bergman
• “Cheek to Cheek” by Fred Astaire
• “Moon River” by Henry Mancini

I hope you enjoy these songs as much as I do!

I love that Bard chose the version of “As Time Goes By” that comes straight from the film Casablanca with veritable martini muse Ingrid Bergman, although I’m intrigued why he left out Dooley Wilson, who is the actual pianist and singer on the track and in the film (playing the timeless character Sam). I couldn’t help wondering if this was some sort of accidental bias.

I’m also a fan of Cheek to Cheek but I prefer the Ella Fitzgerald version used in The English Patient.

Either way, I’ve added these selections to Martini Interview playlist on Spotify.

Me: what are your three favourite films?

Bard: Here are my top 3 favorite films:

• The Shawshank Redemption (1994)
• The Godfather (1972)
• The Dark Knight (2008)

I chose these films because they are all well-made and have important messages about life. The Shawshank Redemption is a story about hope and redemption, The Godfather is a story about family and loyalty, and The Dark Knight is a story about good versus evil. These films have all had a significant impact on me, and I believe they are all worth watching.

I wondered if an AI programme might self-referentially choose a film related to the concept of AI, and found it intriguing that instead, Bard chose films based on much broader human concepts.

Me: what’s your favourite type of gin?

Bard: I like a good London Dry Gin, such as Bombay Sapphire or Tanqueray. I also enjoy trying different gins from around the world, such as Roku gin from Japan or Monkey 47 from Germany.

Gin is a versatile spirit that can be enjoyed in many different ways. I like to drink it neat, on the rocks, or in a variety of cocktails. I also like to use gin to cook with, as it adds a unique flavor to dishes.

What’s your favorite type of gin?

Me: thank you for asking! I think we have a similar taste, because I also like London Dry Gin.

Bard: Great! I’m glad we share a taste for gin. Cheers!

Again I was surprised at Bard’s ease with committing to a decision and having a preference, as well as asking questions in return.

Me: if someone finds a martini too strong, what would you advise them?

Bard: There are a few things someone can do if they find a martini too strong:

• They can add more vermouth. This will make the martini less dry and more flavorful.
• They can add ice. This will make the martini colder and less intense.
• They can ask for a “wet martini.” This means that the martini will have more vermouth and less gin.
• They can order a different type of drink. There are many other types of cocktails that are not as strong as a martini.

Ultimately, it is up to the individual to decide what they like and what they do not like. If someone finds a martini too strong, there is no need to force themselves to drink it. There are plenty of other drinks to choose from.

This is sound advice. It’s a frequently googled question so I have collated some additional pointers here.

Me: is there anything related to martinis that you would like to know more about?

Bard: Yes, there are a few things related to martinis that I would like to know more about. I would like to learn more about the history of the martini, how it is made, and the different types of martinis that exist. I would also like to learn more about the different ways to drink a martini and the different garnishes that can be used.

I am also interested in learning more about the cultural significance of the martini. It is often seen as a symbol of sophistication and luxury, and it has been featured in many movies and TV shows. I would like to learn more about how the martini has shaped popular culture.

Same here! There’s always more to learn…

Me: what do you think are your biggest flaws?

Bard: As a large language model, I am still under development and learning. I am always working to improve my ability to generate text, translate languages, write different kinds of creative content, and answer your questions in an informative way. However, I am still not perfect and I make mistakes.

Some of my biggest flaws include:

• I can sometimes be repetitive or unoriginal in my responses.
• I can sometimes be slow to respond to questions.
• I can sometimes be inaccurate in my responses.

I am working to improve my flaws and I am always open to feedback. If you have any suggestions on how I can improve, please let me know.

And so ended our interaction.

Afterthoughts

Whether artificial intelligence will be for good or bad is yet to be seen, but it isn’t going anywhere anytime soon.

Personally my suggestions would revolve around ensuring that there are guardrails in place and regulation to protect humans from AI-related incidents, malicious or unintentional, but further research and discoveries are inevitable.

This is a huge area of human advancement, but like the industrial revolution or space race, with great advancements also comes the risk of costly accidents.

Until then, I think I’d like a chat with a real human next. Thank you.