What are the three main phases in how Claude generates text?	Tokenization, Prediction, and Sampling.
What happens during the prediction phase of text generation?	Claude determines possible next words and assigns a probability to each option.
How is the next token selected during the sampling phase?	A token is chosen based on the probabilities assigned to all possible next tokens.
What is the purpose of the 'temperature' parameter?	To influence the distribution of probabilities and control which token Claude selects.
What is the typical range for the temperature parameter?	A decimal value between zero and one.
What type of output is produced when the temperature is set to zero?	Deterministic output, where the token with the highest initial probability is always selected.
How does increasing the temperature affect the output?	It increases the chances of selecting tokens with lower initial probabilities, leading to more creativity.
When should a low temperature be used?	For tasks requiring less randomness or deterministic output, such as data extraction.
When should a high temperature be used?	For creative tasks, such as brainstorming, writing, or generating jokes.
How is the temperature adjusted when making a model call?	By passing it as a specific argument (parameter) in the function call.