The AI Scientist Finds a Mechanism
One system tested a surprising biological theory
Aug 31, 2026 · 51 min · 13 segments
The BioRevolution Podcast - Episode 51 Artificial intelligence is increasingly becoming part of the scientific process itself. Beyond analyzing data or predicting molecular structures, emerging AI…
Thibault GeouiGuest
Louise von StechowHost
Andreas HorchlerHost
Can you explain why? Why? Because, you know, I think, okay, so that could be an entire podcast on this topic.

But, you know, when people talk about having a mission when you work in something, you know, like I cannot think about other industry where there is a more important mission than in life science in general and in pharmaceutical industry, because in the end, we're developing drugs, you know, we're developing drugs or patient.

They are for far less because you have maybe 10 drugs against the same indication.

And then from those 4,000 or 5,000, you have maybe 200 to 300 that are actually curing the disease.

So if we go at this pace, we need another 500 years until we cure all diseases.

I would be before we dig into the AI field, and we're extremely interested in that.

But at the same time, when you mentioned this, and I have to ask this question, we're at the crossroads where healthcare systems are... on the edge, where the question, the basic question is, how on earth are we going to pay for this in the future? And at the same time, you have this revolution that is going on with new findings, new drug development, quicker drug developments, probably drug development under a billion euro per drug.

And we have to ask ourselves the question, where do we want to be headed with this?

You know, like yesterday I was listening to the radio, like normal treatment as you are aging.

Like five years ago, there was one treatment that would cost 80,000 euros a year.

And now I think, at least it's in France from the official number, we have something like 40 or 50 or even more.

Can you explain why? Why? Because, you know, I think, okay, so that could be an entire podcast on this topic.

But, you know, when people talk about having a mission when you work in something, you know, like I cannot think about other industry where there is a more important mission than in life science in general and in pharmaceutical industry, because in the end, we're developing drugs, you know, we're developing drugs or patient.

They are for far less because you have maybe 10 drugs against the same indication.

And then from those 4,000 or 5,000, you have maybe 200 to 300 that are actually curing the disease.

So if we go at this pace, we need another 500 years until we cure all diseases.

I would be before we dig into the AI field, and we're extremely interested in that.

But at the same time, when you mentioned this, and I have to ask this question, we're at the crossroads where healthcare systems are... on the edge, where the question, the basic question is, how on earth are we going to pay for this in the future? And at the same time, you have this revolution that is going on with new findings, new drug development, quicker drug developments, probably drug development under a billion euro per drug.

And we have to ask ourselves the question, where do we want to be headed with this?

You know, like yesterday I was listening to the radio, like normal treatment as you are aging.

Like five years ago, there was one treatment that would cost 80,000 euros a year.

And now I think, at least it's in France from the official number, we have something like 40 or 50 or even more.
Every episode on Radar is fully transcribed, speaker-labeled, and rich with metadata. Here is a taste of this one. Try Radar for free to see the rest.
3 of 11
The AI Scientist Finds a Mechanism
One system tested a surprising biological theory
The FDA Catches an AI Hallucination
AI-generated errors can carry serious regulatory accountability
Banning AI Is Stupid
The real challenge is using AI responsibly
+8 more clips · 10 min 17 sec of audio in all
7 of 25
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
All 11 clips — the highlight moments, each cut as its own audio, with a title and a speaker
All 13 segments — the transcript broken into labeled sections, every ad read marked
All 25 topics — jump to every other episode discussing the same subject
Every related episode — other shows Radar links to this one
No account is needed to search Radar.