Concept
Textual learning rate
A textual learning rate is a cap on how much a text-space optimizer may rewrite a natural-language artifact (a prompt, a skill document, an instruction block) in a single optimization step. When you optimize text instead of weights, there is no gradient and no scalar step…
The rest of “Textual learning rate” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→