This is the question researchers at Harvard University attempted to answer when examining the potential that large language models (LLMs) could bring to the energy sector.

LLMs are a type of artificial intelligence that can recognise, summarise, translate, predict and generate content having been trained using very large datasets, such as those that power ChatGPT.

Having already found use cases across multiple industries, a team at Harvard’s John A Paulson School of Engineering and Applied Sciences (SEAS) has now published a study exploring the promise of LLMs to help run and maintain the energy grid.

The research team, which included engineers from Houston-based energy-provider CenterPoint Energy and grid operator Midcontinent Independent System Operator, used GPT models to explore the capabilities of LLMs.

They found that LLMs have many strengths, including the ability to generate logical responses from prompts, to learn based on limited data, to delegate tasks to embedded tools and to...