Sampling Parameters as Substances: An Honest Analogy

Automated excerpt

Every sampling parameter in a language model sits on the same trade-off — how boldly the model picks its next word — and each one has a rough equivalent in how a mind works. The one trade-off behind everything A language model doesn't "know" what to say. At every step it produces a probability for every token it could write next, then picks one. Pick the most likely word every time and the text is safe, correct, boring. Every parameter below just moves the needle between those two poles.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.