that's pretty funny.

> give me 11 random numbers in a set with range 1-10, allowing duplicates

> ChatGPT: [3, 7, 1, 4, 9, 2, 6, 3, 10, 8, 5]

I repeated it three times, 3 and 7 were always the first two elements haha.

(I get why, and get why this is stupid to expect it to do, but it still gave me a laugh.)

in case my comment made someone wonder what the 'right'* way to do this is, if you needed to for some reason.

> give me 11 random numbers in a set with range 1-10, allowing duplicates. if you don't think an LLM can generate properly pseudorandom numbers, then use your tools to generate them.

This caused it to create and execute a python script that returned

  [random.randint(1, 10) for _ in range(11)]

which, of course, worked.

* obviously don't leave it up to the model to decide about whether it can do random numbers. I just wanted to see what it would do..