What does temperature do?
Scores become probabilities, and temperature sharpens or flattens them.
Transcript
A language model does not pick one word. It scores every possible next word, and turns the scores into probabilities.
Then it samples: a random draw, weighted by those probabilities.
Temperature reshapes the probabilities. A low temperature sharpens them, so the top word almost always wins.
A high temperature flattens them, so unlikely words get a real chance.
Run the same prompt several times. At low temperature, the answers are nearly identical.
At high temperature they vary a lot, more creative, but also more likely to wander off.
Low temperature for facts and code. Higher temperature for brainstorming and stories. It is one dial, between reliable and creative.
More in this series
1:14How does AI work?
Neurons and weights, learning from mistakes, and predicting the next word.
1:13How does AI read a sentence?
Tokens, embeddings and attention, stacked in layers to score the next token.
1:17What are billions of parameters?
What a parameter is, how big a billion is, and why big models need racks of GPUs.
1:26How do networks learn from errors?
Loss as a landscape, gradient descent and backpropagation.
1:24How is a chatbot trained?
Pretraining, fine-tuning and human feedback turn a text predictor into an assistant.
1:19How does AI draw pictures?
Diffusion models add noise to learn, then remove it to create, steered by a prompt.
1:15How can AI use your own documents?
Retrieval-augmented generation: embed, retrieve, augment the prompt, generate.
1:14Why does AI make things up?
Likely is not the same as true: gaps, snowballing errors, and what helps.
1:16How much can an AI remember?
The context window, forgetting, the cost of long inputs, and workarounds.
1:09What is an AI agent?
A model in a loop with tools and guardrails.
1:12Can AI be biased?
Skewed data, where bias comes from, proxies, and how to audit and fix it.
1:10What is overfitting?
Underfit, good fit and overfit curves, train vs test error, and the fixes.