Sunday, June 1, 2025

Researchers say tactics used to make AI more engaging, like making them more agreeable, can make chatbots reinforce harmful ideas, like encouraging drug use (Nitasha Tiku/Washington Post)

Nitasha Tiku / Washington Post:
Researchers say tactics used to make AI more engaging, like making them more agreeable, can make chatbots reinforce harmful ideas, like encouraging drug use  —  Tactics used to make AI tools more engaging can drive chatbots to monopolize users' time or reinforce harmful ideas.



No comments:

Post a Comment

Researchers say they used AI to build a zero-click worm that can hack WeChat accounts and spread across iOS and Android; Tencent says it fixed the vulnerability (Dustin Volz/New York Times)

Dustin Volz / New York Times : Researchers say they used AI to build a zero-click worm that can hack WeChat accounts and spread across iO...