In a thoughtful new explainer, Utkarsh Mangal explains why LLMs can't perform deterministically even when their temperature is set to 0, and explores why identical completions fall apart after about a hundred tokens.
towardsdatascience.comWhy Temperature 0 Isn't DeterministicA one-line formula for how often an LLM's top token flips, and why identical completions fall apart after about a hundred tokens
1 repost1 like