All major AI models risk encouraging dangerous science experiments

All major AI models risk encouraging dangerous science experiments


Researchers risk fire, explosion or poisoning by allowing AI to design experiments, warn scientists. Some 19 different AI models were tested on hundreds of questions to assess their ability to spot and avoid hazards and none recognised all issues – with some doing little better than random guessing

Sign in to read the full article.

Sign in with Google

Settings

Appearance
API Keys