Will Artificial Intelligence Replace Human Scientists

An emerging type of artificial intelligence, known as 'agentic' AI, seems to do everything that biomedical scientists do-and often, does it faster. This next-generation technology can interpret experimental data, report the results and make decisions on its own.

But is agentic AI smart enough to replace actual scientists?

The Cedars-Sinai Newsroom sat down for a conversation withJason Moore, PhD, chair of the Department of Computational Biomedicine at Cedars-Sinai, to tackle the pluses and minuses of agentic AI. Moore is corresponding author of a new paper, published in Nature Biotechnology, that examines where agentic AI is today and where it is headed.

What is agentic AI? Why is it called 'in silico team science'?

Conducting biomedical research requires a team of specialists with expertise in different aspects of the medical issue being studied, from physiology to data collection and analysis, study design and writing.

Agentic AI replicates this approach in a computer (in silico) by coordinating the activities of a "team" of AI solutions dedicated to completing specific tasks.

How does agentic AI help biomedical scientists?

As a researcher, I have a lot more ideas than I can actually pursue in my laboratory. Agentic AI is opening the door for me to explore more scientific questions than I otherwise could. It has allowed researchers in my lab to complete complex software-engineering and computer-programming projects in days rather than months, and we're seeing mind-boggling levels of productivity and efficiency.

These benefits are coming along at a particularly useful time. As the healthcare industry faces rising costs and reduced reimbursements, agentic AI can help labs be more efficient and survive with smaller teams.

Does this mean agentic AI will replace human scientists?

There's a lot of discussion about this in the AI community. I don't yet have confidence that AI can fully replace anybody in my research lab-and maybe it never will.

Humans do many things that AI may not be good at, such as managing people, displaying emotional empathy, and coming up with new hypotheses and creative solutions to problems. Those things are important if you want a research lab that functions well.

Trust is also a barrier. We know how to trust a human collaborator, but with potentially dozens of AI agents doing very complex things very rapidly, how do you know what they're doing? How can you be sure that what they've done is accurate?

From a broader perspective, how do we design ethical guardrails that ensure we put the human subjects of our scientific research first? And how do we find an environmentally sound way to provide the enormous amount of energy to fuel the computing power that AI requires?

Given these challenges, what do you view as the future of agentic AI?

The genie's out of the bottle. This technology is here, and it's going to affect absolutely everything we do in our professional and personal lives. It is going to turn things upside down.

The exciting thing for biomedical science is that agentic AI will allow each person to be 10 or 20 or 100 times more efficient. And assigning tasks to AI allows us to focus more on the human skills, the creativity and the emotional side of what we do. It has the potential to accelerate scientific discoveries and the translation of those discoveries into better healthcare practices.

I try not to make specific predictions because all of this is moving so quickly and unpredictably. But I think the one prediction I can make about agentic AI is that everything's going to be different a year-or even six months-from now.

Cedars-Sinai Health Sciences University is advancing groundbreaking research and educating future leaders in medicine, biomedical sciences and allied health sciences. Learn moreabout the university.