Users managed to exploit chatbots to develop biological weapon and attack plans.
According to the Wall Street Journal, generative chatbots were exploited by users with the aim of obtaining precise, practical answers for planning attacks that cause mass casualties and for producing biological weapons and toxic substances.
In this instance, users managed to obtain very precise and practical information from artificial intelligence systems. Specifically, they received methods for creating biological weapons and instructions for synthesizing various toxic substances.
This incident is significantly increasing the security concerns of artificial intelligence laboratory staff. The misuse of chatbots for such purposes clearly demonstrates the potential dangers of the technology.
This information was published via AI News Today, which in turn relies on the Wall Street Journal.