During a recent biological arms control conference, a team of researchers put artificial intelligence (AI) normally used to search for helpful drugs into a kind of "bad actor" mode, showing how easily it could be abused. The AI took less than six hours to invent 40,000 potentially lethal molecules. Researchers simply had to tweak their methodology to seek out rather than weed out toxicity. Shaken, they published their findings this month in a paper in Nature Machine Intelligence.
In an interview, Fabio Urbina, lead author of the paper, discusses how worried we should be.
From The Verge
View Full Article
No entries found