Shows how LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition →-generated program candidates plus evolutionary selection lifted Claude Sonnet 3.5 from 14% to 53.6%. It is a pattern engineers can reuse for test-time search.
Terms in this piece · Glossary
test-time compute — Spending more computation when the model answers — thinking longer, trying multiple attempts — to buy accuracy without training a bigger model.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
