Tag
TROPT is an open-source framework that unifies discrete text-trigger optimization, standardizing development and execution across domains like LLM jailbreaking and model interpretability. It includes over 15 optimizers and 30 recipes, lowering barriers for adoption and advancement.
The article argues that text optimization—modifying prompts, context, memory, and retrieval—should be treated as a legitimate learning mechanism alongside weight optimization, highlighting its sample efficiency and ability to scale via update-time compute.
The author argues that text optimization (prompts, context, memory) is a legitimate and sample-efficient learning mechanism that should be taken more seriously by the ML community, enabling a new scaling axis of update-time compute.