Comment by cma
2 days ago
If it's using Aaronson's approach it shouldn't have any noticeable affect on generations. When it picks between options weighted by probability after the generation of logits, it still follows the probability mass, it just uses a known pseudorandom seed so that when you go back and look at the exact choices you can fingerprint it.
That's exactly right. And as is well understood, a good pseudorandom generator, despite being fully deterministic, is extremely hard to distinguish from randomness, unless you have the algorithm and key (internal state). Quite smart, really.