~> seq 0 250 | par-each {|x| llm "Sample a random number, from 1 to 100."} | save nums.nuon
~> open nums.nuon | where {|x| $x != ""} | each {|x| $x | parse -r '(\d+(?![\d\D]*\d))' | get capture0 | get 0} | str join "\n" | uplot hist
┌ ┐
[ 20.0, 30.0) ┤ 1
[ 30.0, 40.0) ┤ 1
[ 40.0, 50.0) ┤######### 26
[ 50.0, 60.0) ┤################# 48
[ 60.0, 70.0) ┤############### 44
[ 70.0, 80.0) ┤################################### 100
[ 80.0, 90.0) ┤###### 17
└ ┘
GPT-3.5's "random" numbers from [0, 100)
I wonder how well it would correlate with a similar human study.