Several factors have traditionally hampered the effectiveness of agricultural extension services, including limited institutional capacity and reach. Here we assess the potential of large language models (LLMs), specifically Generative Pre-trained Transformer (GPT), to transform agricultural extension. We focus on the ability of LLMs to simplify scientific knowledge and provide personalized, location-specific and data-driven agricultural recommendations. We emphasize shortcomings of this technology, informed by real-life testing of GPT to generate technical advice for Nigerian cassava farmers. To ensure a safe and responsible dissemination of LLM functionality across farming worldwide, we propose an idealized LLM design process with human experts in the loop.

https://doi.org/10.1038/s43016-023-00867-x

Multi standard citation

APAHarvardMLAVancouverChicagoIEEE

Medha Devarehttps://orcid.org/0000-0003-0041-4812

Pieter Pypershttps://orcid.org/0000-0001-8913-0589

https://doi.org/10.1038/s43016-023-00867-x

Natural Resource Management

Agronomy; Cassava; Climate Change; Food Security; Smallholder Farmers

Agricultural Extension; Cassava; Farmers; Technology

Africa; West Africa

Nigeria

Central Africa Hub; Headquarters and Western Africa Hub

Nature Food