Researchers created 26 principles to improve prompting large language models and get better answers, which were tested on models like LLaMA and GPT - you can find out more about these principles and how they work in the paper "Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4". via Hugging Face.
Read next
From new NBER Working paper:
We leverage novel advertising video data and apply new empirical methods to study how banks actively use advertising to build their images, align with their operational strengths, market positions, and the demographics of target customers. These image-building efforts have significant impacts on the demand for
"General Social Agents" by Benjamin Manning and John Horton:
Our approach relies on two key principles: (i) grounding candidate AI agents in theories expected to drive human behavior in the target setting, and (ii) optimizing and then validating AI agents in distinct but related settings presumed to share underlying behavioral
Subscribe to Newsletter
Stay up to date with email notifications of new posts.