Researchers Using AI Came Up with 40,000 New Chemical Weapons Like VX


The Verge spoke with Fabio Urbina, who is a senior scientist at Collaborations Pharmaceuticals, Inc. He wrote a paper on how AI could be used as a force for evil by “bad actors.” It can be used to search for helpful drugs, and the converse is true. His researchers came up with 40,000 new chemical weapons similar to VX within hours, using AI.

Four researchers involved in AI-based drug discovery have now found that the technology could easily be manipulated to search for toxic nerve agents.

The four were asked by the Swiss Federal Institute for Nuclear, Biological, and Chemical Protection to look at whether AI could be used by those with ulterior motives – and their AI came up with 40,000 potentially toxic drugs in six hours.

They have highlighted their concerns in the journal Nature Machine Intelligence.

Researchers didn’t weed out toxicity to come up with the 40,000 new chemical weapons in six hours. They were similar to VX, the most potent nerve agent ever developed.

VX Storage

They were shaken and published their findings in the journal Nature Machine Intelligence.

“At the end of the day, we decided that we kind of want to get ahead of this. Because if it’s possible for us to do it, it’s likely that some adversarial agent somewhere is maybe already thinking about it or in the future is going to think about it. By then, our technology may have progressed even beyond what we can do now. And a lot of it’s just going to be open source — which I fully support: the sharing of science, the sharing of data, the sharing of models. But it’s one of these things where we, as scientists, should take care that what we release is done responsibly.”…

“I don’t want to sound very sensationalist about this, but it is fairly easy for someone to replicate what we did.”

“If you were to Google generative models, you could find a number of put-together one-liner generative models that people have released for free. And then, if you were to search for toxicity datasets, there’s a large number of open-source tox datasets. So if you just combine those two things, and then you know how to code and build machine learning models —  all that requires really is an internet connection and a computer — then, you could easily replicate what we did. And not just for VX, but for pretty much whatever other open-source toxicity datasets exist.”

Since he believes in open science, Mr. Urbino’s only solution to these new VX discoveries is for more scientists to become aware and agree to not use it.


5 1 vote
Article Rating
Notify of
Oldest Most Voted
Inline Feedbacks
View all comments