Hacker News new | ask | show | jobs
by ANewFormation 424 days ago
LLMs are 100% deterministic. The facade of randomness is injected solely by a superfluous rng factor.
1 comments
mdp2021 424 days ago
Even if in the forward pass there would be no "temperature" tilting, the NN training would still be performed through different processes on different implementations, making the outputs "personal".
link