← Jargon

Jargontechnology· 11 claims· 1 episode

metaprompting

Using LLMs to iteratively generate and refine versions of prompts themselves, where one prompt dynamically improves another prompt; essentially having an LLM act as a prompt engineer to enhance its own instructions.

As defined in State-Of-The-Art Prompting For AI Agents


Where it comes up · 1

Most important claims · 10 of 11Search all claims for “metaprompting” →