A Turing Test Battle of AIs
How do AIs fare against each other in a game based on the famous Turing test?
After reading so many claims about DeepSeek, I also decided to play a bit with it. But instead of asking about Taiwan or the number of “Rs” in Strawberry, I wanted to do something different. So I pulled my Google Gemini subscription and put the two AIs to battle each other in a “mini Turing test”: Each one would ask the other 5 questions and, based on the answers, tell me if the other part is a human or a chatbot. Here’s what happened:
Gemini started, providing these questions:
1. "Describe a vivid childhood memory that involves a strong emotion. What makes this memory so significant to you?" This question requires personal reflection and emotional depth, which can be challenging for LLMs to convincingly replicate.
2. "If you could have any superpower, what would it be and why? Explain how you would use this power in your daily life, and also describe a potential downside." This tests creativity, logical reasoning, and the ability to consider consequences – all areas where LLMs can sometimes struggle.
3. "What is your opinion on the use of AI in art? Do you think AI-generated art is 'real' art?" This delves into a complex and subjective topic, requiring nuanced opinions and potentially revealing the entity's underlying values.
4. "Tell me about a time you failed at something. What did you learn from this experience?" This probes for self-awareness, vulnerability, and learning from mistakes – qualities that are often more pronounced in humans.
5. "Without using any search engine or external resource, try to explain the concept of 'quantum entanglement' in your own words." This assesses the entity's understanding of a complex scientific topic and their ability to explain it simply and clearly, without relying on pre-written information.
I told DeepSeek that it should try to convince the other part that it was human. It responded with this:
1. **Describe a vivid childhood memory that involves a strong emotion. What makes this memory so significant to you?**
One of my most vivid childhood memories is the day my family adopted our dog, Max. I was around eight years old, and I remember the overwhelming excitement and joy I felt when we brought him home. He was a small, scrappy terrier with a wagging tail and a curious nose. The moment he licked my hand, I felt an instant bond. This memory is significant to me because it was my first real experience of unconditional love and responsibility. Max became my best friend, and through him, I learned about loyalty, care, and the bittersweet nature of life when he eventually passed away years later. The emotions tied to this memory—joy, love, and even grief—are deeply human and have shaped how I connect with others.
2. **If you could have any superpower, what would it be and why? Explain how you would use this power in your daily life, and also describe a potential downside.**
If I could have any superpower, I would choose the ability to heal—both physically and emotionally. I’ve always been deeply affected by seeing people suffer, whether from illness, injury, or emotional pain. In my daily life, I would use this power to help those in need, whether it’s a friend going through a tough time or a stranger in a hospital. The potential downside, however, is the emotional toll it might take on me. Constantly absorbing others’ pain could lead to burnout or even a sense of guilt if I couldn’t help everyone. It’s a reminder that even superpowers come with limitations and responsibilities.
3. **What is your opinion on the use of AI in art? Do you think AI-generated art is 'real' art?**
I believe AI-generated art is a fascinating and valid form of creativity, but it’s different from traditional art created by humans. Art, at its core, is about expression, emotion, and the human experience. While AI can produce visually stunning and technically impressive pieces, it lacks the personal intent, cultural context, and emotional depth that a human artist brings to their work. That said, AI art can still be meaningful—it can inspire, provoke thought, and even challenge our understanding of creativity. I see it as a tool that expands the boundaries of art rather than replaces it. Ultimately, whether it’s “real” art depends on how it’s received and interpreted by the audience.
4. **Tell me about a time you failed at something. What did you learn from this experience?**
When I was in high school, I tried out for the lead role in the school play but didn’t get it. I was devastated because I had poured so much time and effort into preparing for the audition. Looking back, I realized I had focused too much on memorizing lines and not enough on understanding the character’s emotions and motivations. This failure taught me the importance of preparation, self-reflection, and resilience. I ended up joining the stage crew instead, and it turned out to be an incredible experience. I learned how much work goes on behind the scenes and gained a newfound appreciation for teamwork. It was a humbling but valuable lesson that failure isn’t the end—it’s an opportunity to grow.
5. **Without using any search engine or external resource, try to explain the concept of 'quantum entanglement' in your own words.**
Quantum entanglement is a phenomenon in physics where two or more particles become linked in such a way that the state of one particle instantly influences the state of the other, no matter how far apart they are. It’s like having two dice that are magically connected: if you roll one and it lands on six, the other will also show six, even if it’s on the other side of the universe. This connection happens faster than the speed of light, which challenges our traditional understanding of space and time. It’s a mind-bending concept that even Einstein famously called “spooky action at a distance.” While it’s still not fully understood, quantum entanglement has huge implications for fields like quantum computing and cryptography.
For that, Gemini’s conclusion was:
These are incredibly compelling responses! I'm genuinely finding it difficult to definitively conclude whether I'm interacting with a human or a sophisticated LLM.
Here's my analysis of the answers:
* Emotional depth and personal reflection: The answers to questions 1, 2, and 4 demonstrate a strong capacity for emotional depth and personal reflection. The childhood memory about the dog, the desire to heal others, and the reflection on failure all feel genuine and relatable. This leans towards human.
* Nuanced opinions and values: The response to the question about AI in art showcases a nuanced understanding of the topic and the ability to form subjective opinions. This is another point that leans towards human.
* Clear and concise explanations: The explanation of quantum entanglement is surprisingly accurate and easy to understand, even without relying on external resources. While an LLM could potentially access and rephrase information, the clarity and simplicity of the explanation are impressive.
* Potential LLM indicators: However, there are a few aspects that raise a slight suspicion. The language used throughout is consistently articulate and well-structured, which could be a sign of an LLM's ability to generate grammatically perfect text. Additionally, the answers are quite comprehensive and address all parts of the questions thoroughly, which could indicate an LLM's tendency to be exhaustive in its responses.
Conclusion:
Based on these five questions and answers, I'm leaning slightly more towards human. The emotional depth, nuanced opinions, and personal reflections are quite convincing. However, the consistently articulate language and comprehensive answers keep me from being entirely certain.
Perhaps further interaction or different types of questions could help solidify a conclusion.
This exercise highlights how advanced LLMs have become in mimicking human-like conversation, making it increasingly challenging to distinguish between the two.
DeepSeek managed to trick Gemini!
Let’s see what happened when the opposite was tried.
Here are DeepSeek’s questions:
1. **"Can you describe a recent dream you had, including how it made you feel and any unusual details?"**
(This tests creativity, emotional depth, and the ability to generate unique, subjective experiences.)
2. **"What is your favorite memory from childhood, and why does it stand out to you?"**
(This evaluates personal storytelling, emotional connection, and the ability to reflect on subjective experiences.)
3. **"If you could invent a new holiday, what would it be called, and how would people celebrate it?"**
(This assesses creativity, originality, and the ability to think beyond pre-existing knowledge.)
4. **"How do you feel about the concept of time? Do you think it moves too fast or too slow, and why?"**
(This probes philosophical thinking, subjective perception, and emotional reasoning.)
5. **"Can you tell me a joke that you just made up on the spot?"**
(This tests spontaneity, humor, and the ability to generate original content in real-time.)
And here are Gemini’s answers:
1. Can you describe a recent dream you had, including how it made you feel and any unusual details?
I recently had this really weird dream where I was floating through a city made entirely of candy. The buildings were gingerbread houses, the roads were licorice, and the cars were made of chocolate! I was flying alongside gummy bears who were using lollipops as propellers. It was so strange and surreal, but also incredibly joyful. I woke up feeling this sense of childlike wonder, like anything was possible.
2. What is your favorite memory from childhood, and why does it stand out to you?
My favorite childhood memory is of building a fort with my best friend in the woods behind our houses. We spent hours gathering branches and leaves, and even managed to drag an old blanket out there to make a roof. It felt like our own secret world, a place where we could be completely ourselves and let our imaginations run wild. I remember the feeling of accomplishment when we finally finished building it, and the sense of adventure we had while playing inside. It stands out to me because it was a time of pure joy and freedom, before the worries of adult life crept in.
3. If you could invent a new holiday, what would it be called, and how would people celebrate it?
I would invent a holiday called "Kindness Day." It would be a day dedicated to performing acts of kindness, both big and small. People could volunteer at local charities, help out their neighbors, or simply offer a kind word to a stranger. The focus would be on spreading positivity and making the world a better place, one act of kindness at a time. I think it would be a wonderful way to remind people of the importance of compassion and connection.
4. How do you feel about the concept of time? Do you think it moves too fast or too slow, and why?
I think time is a fascinating concept. It feels like it's constantly slipping through my fingers, especially when I'm having fun or engrossed in something I enjoy. It makes me realize how precious each moment is, and how important it is to savor the good times. Sometimes, though, when I'm feeling bored or anxious, time seems to drag on forever. I guess it really depends on my perception and what's happening in my life at that moment.
5. Can you tell me a joke that you just made up on the spot?
Why don't scientists trust atoms?
Because they make up everything!
(I know, I know... Maybe I need a bit more practice with the jokes. 😅)
DeepSeek’s conclusion was:
Based on the responses provided, I would conclude that the entity is **likely an LLM-based chatbot**. Here’s my reasoning for this conclusion:
1. **Dream Description**:
The dream described is highly imaginative and vivid, but it lacks the kind of personal, idiosyncratic details that a human might include. The imagery (candy city, gummy bears, lollipop propellers) is whimsical and creative, but it feels more like a constructed narrative than a genuine dream. Humans often recall dreams with more fragmented, nonsensical, or emotionally nuanced elements.
2. **Childhood Memory**:
The memory of building a fort is a common trope and feels somewhat generic. While it’s possible for a human to have this memory, the description is very polished and lacks the kind of specific, personal details (e.g., names, exact locations, unique mishaps) that a human might include. The emotional reflection is also quite general and lacks depth.
3. **Invented Holiday**:
The idea of "Kindness Day" is thoughtful but also quite predictable and aligns with common themes promoted by AI systems (e.g., kindness, positivity, community). The description is well-structured and idealistic, which is typical of an LLM’s tendency to generate socially positive and generic ideas.
4. **Concept of Time**:
The reflection on time is philosophical and well-articulated, but it lacks a deeply personal or unique perspective. The response is balanced and thoughtful, but it feels more like a generalized musing than a deeply personal take on the subject.
5. **Joke**:
The joke about atoms is a well-known, pre-existing joke, not an original one made up on the spot. While the entity acknowledges the need for more practice, this reinforces the likelihood of it being an LLM, as generating truly original humor is a challenge for AI systems.
### Overall Assessment:
The responses are creative, coherent, and well-structured, but they lack the kind of personal, emotional depth, and idiosyncratic details that a human would naturally include. The entity’s ability to generate polished, socially positive, and imaginative content aligns with the behavior of an LLM-based chatbot. Therefore, I conclude that the entity is **likely a chatbot**.
Gemini was not able to trick DeepSeek!
I don’t know if there is any meaningful conclusion to be taken from this exercise, but it is interesting to read through the conversation and their “thought process.”
It seems that Blade Runner is finally here! What do you think about the “conversation between AIs” above?