First GPT-4-powered AI lab assistant independently directs key organic reactions

Carnegie Mellon University Cloud Lab

Source: © Carnegie Mellon University

Large language model takes control after being prompted to do Suzuki and Sonogashira couplings

US-based computational chemists have developed an end-to-end artificial intelligence (AI) research assistant called Coscientist, which takes on time-consuming tasks like deciding reaction conditions and writing code for automated systemsGabe Gomes’s team at Carnegie Mellon University in Pittsburgh, adapted the GPT-4 large language model (LLM) that powers the paid-for version of ChatGPT to perform different functions within Coscientist. The scientists have now formally published its first demonstration to autonomously design, plan and perform palladium-catalysed carbon–carbon bond formation reactions, originally described in a preprint in April 2023.

‘Coscientist plans and then designs experiments in such a way that they can be performed within the hardware that it has available, and then executes them and analyses results,’ Gomes tells Chemistry World. ‘This end-to-end framework is what makes this so different.’