> The "randomness" of llms you are probably experiencing stems from the autoregressive completion, which samples from probabilities for a temperature T>0 (which is very common because it makes sense in chat applications).
Even that “random” sampling is deterministic, in that if you use the same PRNG algorithm with the same random seed, then (all else being equal) you should get the same results every time.
To get genuine nondeterminism, you need an external source of randomness, such as thermal noise, keystroke timing, etc. (Even whether that is really non-deterministic depends on a whole lot of contested issues in philosophy and physics, but at least we can say it is non-deterministic for all practical purposes.)
Even that “random” sampling is deterministic, in that if you use the same PRNG algorithm with the same random seed, then (all else being equal) you should get the same results every time.
To get genuine nondeterminism, you need an external source of randomness, such as thermal noise, keystroke timing, etc. (Even whether that is really non-deterministic depends on a whole lot of contested issues in philosophy and physics, but at least we can say it is non-deterministic for all practical purposes.)