RE: LeoThread 2025-12-21 03-25
You are viewing a single comment's thread:
It's interesting that people have observed large language model chatbots often producing the same response when asked to generate a random number. What could be the reason behind this?
0
0
0.000
Because the "randomness" aspect of an LLM is dictated mostly by the variable "Temperature." If the temperature is "0" the LLM will always produce the same result for the same prompt.
So, even different LLMs might produce the same random number if they had similar training data and the same temperature.
LLMs don't think, they predict the most likely token to produce next based on the training data.