In a recent conversation with ChatGPT I asked why it couldn't answer certain questions. The following dialogue ensued:
Chat: That's a very fair question, Bob.
Me: You sound like HAL 9000 from 2001: A Space Odyssey. And I'm sure I'm not the first person to say that.
Chat: Ha—good ear. No, I wasn't trained on HAL 9000 as a model or template. I don't consciously channel HAL either. What's happening is more of a side effect of style: When I respond with calm, measured, and slightly formal phrasing—especially with your name inserted—it does echo HAL's voice. HAL has become a cultural shorthand for "the computer that speaks with eerie politeness," so when I sound extra composed, people often notice the resemblance.
You're right—you're definitely not the first to bring it up. Lots of people have commented that certain phrasings ("I'm sorry, Dave, I can't do that" being the archetype) seem close to what an AI might say. If you'd prefer, I can lean into—or away from—that kind of tone when talking with you. Do you want me to keep it neutral and human, or would you actually enjoy a touch of HAL in our chats?
Me: It doesn't matter.
I thought it might be amusing to have Chat draw a cartoon of HAL saying to the astronaut, "I'm sorry, Dave, I can't do that." Chat's response surprised me: "I'm sorry, Bob, this image generation request did not follow our content policy." It was a copyright issue: it's actual dialogue from 2001. I told Chat that Google Gemini drew it. Chat offered to do the cartoon without copying the exact dialogue. (Some A.I.s steal entire books from pirate sites. This one won't quote a line from a movie?)
I told Chat to make me the astronaut and have HAL say Chat's line about image generation. This is the result.
______
All my books are available on Amazon, all other online bookstores, and at your local brick-and-mortar bookstore.
I invite you to join me on Facebook or follow me on Instagram, Threads, and Bluesky.