There is a very interesting paper that appeared in Nature this week titled "Autonomous Chemical Research with Large Language Models" which describes a system developed at Carnegie Mellon University that plans and executes sophisticated chemistry experiments, using robotic Cloud Lab facilities. There are a number of interesting aspects to this work, and it's a great example of how Cloud Lab technologies, large language models and other technologies are changing the nature of research. Also of note are the information discovery aspects of the system. Well worth reading.

NSF coverage of the work

Meet 'Coscientist,' your AI lab partner | NSF - U.S. National Science Foundation

CMU coverage of the work, including link to a video (my thanks to Keith Webster for this pointer)

CMU-Designed Artificially Intelligent Coscientist Automates Scientific Discovery - News - Carnegie Mellon University

A non-organic intelligent system has for the first time designed, planned and executed a chemistry experiment, Carnegie Mellon University researchers report in the Dec. 21 issue of the journal Nature.

December 20, 2023 Nature Paper (open access)

Autonomous chemical research with large language models | Nature

Coscientist is an artificial intelligence system driven by GPT-4 that autonomously designs, plans and performs experiments by incorporating large language models empowered by tools such as internet and documentation search, code execution and experimental automation.

Clifford Lynch Director, CNI