[mikequinlan]

The prompt doesn't say to pick a random number. I asked to pick a number from 1-1000 and it chose 7,381. Then I asked why it picked that number and it said

Nothing mystical, I’m afraid. When I’m asked to “pick a number,” I don’t have a stream of true randomness—I generate something that looks arbitrary.

In this case, I leaned toward:

• something comfortably away from the edges (not near 1 or 10,000),

• not a round or patterned number (so, not 7,000 or 7,777),

• and with a bit of internal irregularity (7-3-8-2 has no obvious rhythm).

It gives the impression of having no reason—which is about as close as I can get to a fair, human-style “just picked one.”

[throw310822]

Not sure why you have been downvoted. While the LLM's introspection can't be trusted, that's indeed what happens: asked to generate a random number, the LLM picks one that feels random enough: not a round one, not too central or extreme, no patterns, not a known one. It ends up being always the same.

[HeavyStorm]

It doesn't "pick" anything. It produces the most likely number after this question based on the data it has been trained with! Reasoning models might pick in a sense that they will come up the the rules (like the grand parent post shows), but still it will produce the "most likely" number after the reasoning.