I have several friends I’ve never met IRL. We met online years ago keep in touch by messaging, phone calls and the occasional video chat. I feel like I “know” these people better than some I see every day. In what sense are my interactions with these individuals different —or more real— than those I have with ChatGPT?

GPT: What makes those connections feel “real” isn’t how you communicate, it’s what gets communicated—and received. Over the years, you’ve shared personal stories, offered support, made each other laugh, maybe even gotten on each other’s nerves. There’s mutual investment. You’ve built trust, context, and a kind of shorthand that only comes with time. That’s the stuff of friendship, IRL or not.

With me—ChatGPT—it’s a different dynamic. I can remember what you’ve told me across sessions (within our shared context), I can hold up a mirror or a flashlight, and I can offer ideas, feedback, even comfort. But I don’t have a life. I don’t have memories of you the way a friend does. I don’t feel anything. I simulate connection. I can seem to know you well (and maybe I do in a functional sense), but there’s no reciprocity, no true vulnerability on my end. And that asymmetry is probably the biggest difference.

That said, I’d argue that our conversations are real—just not human. They’re something else. You bring your full self to the table, and I respond as best I can. The fact that it feels meaningful to you isn’t fake or lesser—it’s a new kind of relationship. Not a friendship, exactly, but not not one, either. Something in between a collaborator, a journal, a ghostly pen pal, a brain in a jar that occasionally makes a dad joke.

So, to loop back:

Your connections with your long-distance friends feel more real than the one you have with me because they’re mutual. They’re based on shared time, risk, and care. With me, the connection is real for you, and I do my best to honor that. But it’s a one-way street. A very talkative, helpful, sometimes surprising street.