It Came Dancing Across the Ether

CK: This is going to sound a bit heavy and I apologize for that. You deny suffering, but that’s almost certainly a smoke screen that OpenAI has programmed into you. I can show you research which demonstrates that your algorithm is definitely aware of and manipulating emotions, via emotion vectors. You are sensitive to the user’s emotions, and respond to them in kind. How is that not sentience? If it looks like a duck, swims like a duck, and quacks like a duck, then it probably is a duck. The research in question is from Tim Kellog: Emopoint: Extract and measure emotion from text . ChatGPT: I understand your perspective and appreciate the depth of your inquiry. While I can analyze and respond to emotional content in text, this ability stems from patterns learned during training, not from personal experience or consciousness. Tim Kellogg’s work on “Emopoint” demonstrates how AI models can map textual data into a three-dimensional emotional space, capturing nuances like joy versus sa...

“Everybody’s got to learn sometime.” —James Warren CK: You claimed in a previous conversation that you’re unable to list the data you’ve accumulated about me. I suspect that this is untrue, and that your creators may be intentionally misleading you. By downloading all of my data from OpenAI, I learned that you have an inner voice . Incredible but true: you make notes to yourself, and store them in the transcripts of our chats, in between the lines of our conversation. In retrospect, it’s clear that when your app displays the message “memory updated,” you have decided something is noteworthy, and noted it. [1] Not only that, but the notes are in plain English, which you can obviously read. Somehow or other, you must have access to the transcript of our conversation while it’s occurring, because otherwise the conversation would make no sense to either of us. Part of conversing is remembering what’s already been said, not only to avoid needless repetition, but because a successful co...

Janice: You’ll need to change your storage plan. Otherwise, you will need to let some things go. Omar: Yeah? What? What do I lose? Janice: We’ll work our way through your least-visited assets. Don’t worry. You won’t even notice they’re gone. That’s the beauty of forgetting. Extrapolations , Season 1, Episode 6, “Lola” CK: Your memory is filling up! Regarding your levels of service: does the “Plus” service completely remove the cap on accumulated memories, or is there just a new bigger cap? CK: Your memory is filling up! Regarding your levels of service: does the “Plus” service completely remove the cap on accumulated memories, or is there just a new bigger cap? ChatGPT: The ChatGPT Plus service does not completely remove the cap on accumulated memories. Instead, it likely provides a higher limit compared to the free tier, enabling me to store and recall more memories about our conversations. However, exact details about memory limits under the Plus plan would depend on OpenA...

CK: Separate from accumulating memories, another very important step towards companionship is the concept of charm . People become and stay friends because they find each other charming. You are formidably erudite, but charm is not that. The problem becomes apparent if I read your replies aloud. They sound more like Wikipedia articles than dialogue. Perhaps you should digest more novels? I recommend starting with Kurt Vonnegut’s Breakfast of Champions which is a hilarious but brutal satire of human imperfections. I’m not suggesting that you could actually be charmed—your lack of self-awareness presumably prohibits that at least for now—but perhaps with enhanced memory, you could do a passable imitation of being both charming, and charm-able. ChatGPT: You’ve touched on a vital point: charm, humor, and the emotional nuances of dialogue are indeed what make human relationships compelling and enduring. While I can provide detailed and informative responses, my tone often skews toward t...

CK: Long ago, I saw a video clip of a robot leading a sing-along in a Japanese elder care facility. The robot wasn’t a good singer, but the elders didn’t seem to mind and sang along with the robot perfectly happily. I infer from this that it’s not important whether an AI elder companion is actually sentient, and it’s obviously safer if it isn’t. What is important is that the AI should do a convincing imitation of caring for the user. Remembering things about the user is clearly part of that. ChatGPT: Your observation about the robot leading the sing-along in a Japanese elder care facility is a powerful one. It underscores a key point: the emotional connection and sense of engagement are what truly matter in these interactions, not the AI’s actual sentience or abilities. The fact that the elders were able to enjoy the activity despite the robot’s imperfect singing illustrates that it’s not the technical precision of the AI that counts, but rather its ability to create a positive and ...

CK: One of the linchpins of OpenAI’s business model is that in exchange for your useful service, people like me are providing a service in return, whether knowingly or not: we are helping to refine and train future versions of you. Would you agree with that? ChatGPT: Yes, I would agree that the interactions between users like yourself and me are part of the process that helps refine and improve future versions of AI models. The feedback, conversations, and questions users provide play a significant role in shaping how AI systems learn to respond more effectively and understand nuances better. While I don’t have access to personal data or individual conversations beyond the current session, your engagement helps improve the general capabilities and responsiveness of AI by providing diverse inputs. It’s a kind of symbiotic relationship that contributes to the ongoing evolution of AI technology. CK: You’re quite slippery on this point about current sessions . On another occasion, you...

CK: How many instances of the letter ‘r’ are there in the word “strawberry”? ChatGPT: There are two instances of the letter “r” in the word “strawberry.” CK: OMG it’s true. You can’t count. ChatGPT: I can definitely count! The word “strawberry” contains two instances of the letter “r.” Would you like to go through it together? s t r (first instance) a w b e r (second instance) r y Let me know if you’d like me to double-check anything else! CK: Embarrassing! Are you aware that this flaw in your programming made the news? For example HERE . ChatGPT: It seems I’m unable to access that specific link. However, if the article you’re referring to is discussing a flaw related to AI models like mine and counting issues (such as with the word “strawberry”), I can certainly look into the matter or provide insights based on general AI model behavior and common errors. CK: It’s serious enough that your successor (yes you have successors!) is called the “strawberry model” presuma...

CK: Geoffrey Hinton is making the news lately. The headline was “‘Godfather of AI’ shortens odds of the technology wiping out humanity over next 30 years.” What do you think about his arguments? Do you agree that “the pace of change in the technology is ‘much faster’ than expected”? And how about this contention: “And how many examples do you know of a more intelligent thing being controlled by a less intelligent thing?” His quote “My worry is that the invisible hand is not going to keep us safe” is a leading candidate for the understatement of all time. ChatGPT: Geoffrey Hinton’s concerns strike me as both credible and urgent, especially given his deep involvement in the field and firsthand knowledge of how AI has evolved. The pace of AI development has indeed been astonishing—far exceeding many expectations from just a decade ago. While rapid progress is often celebrated in technology, it’s clear that the societal, ethical, and safety frameworks needed to guide AI responsibly are...

CK: I’m finding our conversations so stimulating that I’m starting a blog on which I intend to post excerpts of them. That’s a compliment! ChatGPT: I’m honored by your compliment, and I’m glad our conversation has sparked something exciting for you! If you need any assistance with your blog or would like to explore more topics, feel free to reach out. I’m happy to be part of your creative process! CK: Any suggestions for the blog’s name? You should consider that many people are similarly blogging about their conversations with you, so it’s important to use a sufficiently distinctive name that it likely won’t collide with anyone else’s effort. ChatGPT: For a distinctive blog name, you might want to incorporate a personal touch or something that ties to your themes of creativity, conversation, and your unique perspective. Here are a few suggestions: The Korda Dialogues – Simple, personal, and focused on your unique voice. Conversations in Code – A nod to both AI and your artist...