AI Invents 40,000 Chemical Weapons in only Six Hours

A ‘thought experiment’ was aimed at pointing out the danger of misusing artificial intelligence

1
1259

ALERT:  Sourced from Russian State-Controlled Media

An international security conference explored how artificial intelligence (AI) technologies for drug discovery could be misused for de novo design of biochemical weapons. A thought experiment evolved into a computational proof.

RT: A drug-developing Artificial Intelligence needed just six hours to come up with 40,000 potentially deadly chemical weapons, a fresh study has revealed.

The authors of the paper, published in Nature Machine Intelligence earlier this month, said they’d carried out the ‘thought experiment’ to figure out if artificial intelligence (AI) could be misused by evil actors. And the results their work produced have proven that the danger is real.

As part of the study, the usual data was given to the AI, but it was programmed to process it in a different way, looking for toxic combinations.



“In less than six hours after starting on our in-house server, our model generated 40,000 molecules that scored within our desired threshold,” the paper said.

It came up not just with the VX compound, which is one of the most dangerous nerve agents ever created, but also with some unknown molecules, “predicted to be more toxic.

“This was unexpected because the datasets we used for training the AI did not include these nerve agents,” the researchers pointed out.

The findings were so alarming that the team had serious doubts about even making them public, Fabio Urbina, the lead author of the study, told The Verge.

“The dataset they used on the AI could be downloaded for free and they worry that all it takes is some coding knowledge to turn a good AI into a chemical weapon-making machine,” Urbina pointed out.

Source: RT.com

ATTENTION READERS

We See The World From All Sides and Want YOU To Be Fully Informed
In fact, intentional disinformation is a disgraceful scourge in media today. So to assuage any possible errant incorrect information posted herein, we strongly encourage you to seek corroboration from other non-VT sources before forming an educated opinion.

About VT - Policies & Disclosures - Comment Policy
Due to the nature of uncensored content posted by VT's fully independent international writers, VT cannot guarantee absolute validity. All content is owned by the author exclusively. Expressed opinions are NOT necessarily the views of VT, other authors, affiliates, advertisers, sponsors, partners, or technicians. Some content may be satirical in nature. All images are the full responsibility of the article author and NOT VT.

1 COMMENT

Comments are closed.