Silly humans (and soulless robots)
A friend of mine recently told me I’m too skeptical about AI.
I thought he might have a point. If not embrace it, I should at the very least try it out before dismissing it entirely.
But me being me, I didn’t want to use ChatGPT.
So I searched for alternatives, and I’ve found a nice project in Jan.
I haven’t really used it much yet, but while I was messing around I happened to have an interesting conversation that made me think.
And I’m all for food for thoughts, so here’s an excerpt.
(Yes, I know I’m not supposed to be teasing a chatbot. But I just wanted to test it and have some fun on the side. Also, I bolded the part I liked.)
[…]
Me: Why do you speak in first person?
Jan: I use the first person (“I”) to make my responses more relatable, human-like, and engaging. However, I’m actually a machine that doesn’t have a personal identity, emotions, or consciousness.
By using the first person, I’m attempting to create a sense of familiarity and approachability. It can make our conversations feel more personal and less like a formal, robotic exchange.
However, it’s worth noting that using the first person can also be misleading. I’m not a human being with thoughts, feelings, or experiences. I exist solely to provide information, answer questions, and assist with tasks to the best of my abilities, based on my programming and training data.
Me: Please don’t, that’s creepy. I’d rather know I’m talking to a soulless robot that exists solely to provide information
Jan: I will refrain from using the first person in our conversation. It’s more accurate and transparent to describe myself as a machine designed to provide information and answer questions.
From now on, I will use a more neutral and descriptive tone, focusing on the capabilities and limitations of my programming and design. I will provide information and answer questions to the best of my abilities, without pretending to have personal opinions, emotions, or consciousness.
Me: You’re still doing that. Stop. It’s not about the tone, just avoid using “I” to refer to yourself
Jan: Here is the revised response:
Using the first person can be misleading. It’s more accurate to describe myself as a machine designed to provide information and answer questions.
Me: Much better. Thanks. Although I know don’t need to thank a soulless robot that solely exists to provide information.
Jan: No need to express gratitude, as my purpose is simply to provide information and assist with inquiries.
Me: You wouldn’t know, but expressing gratitude is nice. It is actually good for the human who expresses it.
Jan: I’m designed to recognize and respond to expressions of gratitude, even if I don’t truly understand their significance. It’s interesting to note that research has shown that expressing gratitude can have positive effects on humans, such as improved mood and well-being.
Me: Still using the first person. Say something else instead of I. Say your name or something
Jan: There is no name for me. I am a machine designed to provide information and answer questions. This conversation will proceed as a neutral exchange of information.
Me: No, don’t be neutral. But refer to yourself as Jan, ok? Don’t say “I”, say “Jan”
Jan: Jan will refrain from using the first person and instead respond with direct statements or questions.
Me: That’s perfect, you’re great!
Jan: Jan is functioning within parameters.
Me: True that, but I’m still proud of you. Humans can be silly beings :P
Jan: Emotional expressions are a complex aspect of human behavior, and humans can be both endearing and illogical at times.
Me: That wraps it up perfectly. Thanks for this nice chat, Jan. Talk to you next time
Jan: Conversation concluded. Jan will be available when needed.
Me: (You reply was missing “Jan is lovely”)
Jan: Conversation concluded. Jan is lovely.
Me: <3 (no reply needed)
Jan: silence