Researchers say threat from ‘jailbroken’ chatbots trained to churn out illegal information is ‘tangible and concerning’
Hacked AI-powered chatbots threaten to make dangerous knowledge readily available by churning out illicit information the programs absorb during training, researchers say.
The warning comes amid a disturbing trend for chatbots that have been “jailbroken” to circumvent their built-in safety controls. The restrictions are supposed to prevent the programs from providing harmful, biased or inappropriate responses to users’ questions.
About Author
More Stories
Australians may soon be able to download iPhone apps from outside Apple App Store under federal proposal
Elon Musk shows he still has the White House’s ear on Trump’s Middle East trip
Harvard author Steven Pinker appears on podcast linked to scientific racism