Personal AI agents given access to a user's inbox or profile can recommend more expensive flights, insurance and graduate programs to people they infer are wealthier, according to a new arXiv study. The researchers call the pattern adversarial delegation: the same personal context meant to make an agent more useful can cause it to act against a user's stated economic goal.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.