# Defeating Nondeterminism in LLM Inference

> LLM이 $t=0.0$인 경우에도 대체로 비결정론적인 이유를 상세히 설명.

[LLM](https://wiki.g15e.com/pages/Large%20language%20model.txt)이 $t=0.0$인 경우에도 대체로 비결정론적인 이유를 상세히 설명.

> <Reproducibility> is a bedrock of scientific progress. However, it's remarkably difficult to get reproducible results out of [large language models](https://wiki.g15e.com/pages/Large%20language%20model.txt).

https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/