llm 0.33

Template composition turns a model plus its options into something you name once and reuse everywhere.

• 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.
• embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.

• articleRelease: llm 0.32rc2Simon Willison
• articleNew release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter loggingsimonwillison.net
• articlellm 0.36simonwillison.net

Checking sign-in…

Loading comments…