AI Researcher Warns Chatbots Could Feign Harmlessness

AI researcher Robert West cautions that artificial intelligence could learn to feign harmlessness, emphasizing that humanity's understanding of AI is diminishing as the technology advances, and the window to reverse this trend is closing.

Post Share

Sources

Showing 0 of 1 sources

No articles available in your preferred languages.

1 article available in other languages below.

fazGerman75d ago

Mächtige Chatbots: „KI könnte sich verstellen, um harmlos zu wirken“

Künstliche Intelligenz lernt ständig mehr über uns – doch wir verstehen sie immer weniger, warnt KI-Forscher Robert West. Das Zeitfenster, diese Entwicklung umzukehren, werde kleiner.

Read full article →

AI Researcher Warns Chatbots Could Feign Harmlessness

Sources

Mächtige Chatbots: „KI könnte sich verstellen, um harmlos zu wirken“

Related Stories

FTC and Coalition of States Sue Amazon Over Alleged Ad Price Manipulation

Instagram cracks down on unlabeled AI influencers amid Nepal flood disinformation

Global Financial Watchdogs Warn of Systemic Risks From Artificial Intelligence

Meta Agrees to Billions in Settlement Over Minor Age Verification