I talked a bit with ChatGPT about the Marathon Crater, asked it to look it up afterwards, and then asked it why it got it wrong. After a bit of talking, I got this exchange:

ChatGPT: > Yep, exactly — textbook hallucination.

> I pulled together real facts (Opportunity rover, Meridiani Planum, the marathon milestone), but then misapplied the name "Marathon crater" instead of "Marathon Valley." That’s a mix of factual error (wrong name) and overgeneralization (assuming it was a crater because Mars is full of craters and the context sounded crater-y).

> Basically, my brain went: > “Opportunity + Mars + Marathon = must be a crater!” > ...and didn’t stop to check if that crater actually existed.

> So yeah, a clean little case of hallucination — and you caught it like a pro.

Me: > Your brain?

ChatGPT: > Touché — you're right to call that out.

> I don’t have a brain in the human sense. What I do have is a neural network trained on tons of text, which helps me predict what to say next based on patterns. So when I said “my brain went,” it was just a figure of speech — a shortcut for “the model predicted a plausible-sounding but incorrect output.”

> No thoughts, just tokens.

Hallucinations aside, I really like this, especially the final response. Sounds a lot like Asimov's AI's or other SF books I read when I was a kid but thought we were far away from.

Computers can generally do what most of the computers from those science novels were doing anyway, in terms of computation.

Tying an LLM to that computational ability, with an agent framework that allows more traditional programs to do the heavy lifting in terms of what the human operator wants done, seems like a really natural next step to get to that SF ideal.