WASHINGTON, D.C. – Experts have long warned about the threat posed by artificial intelligence (AI) going rogue, but a new research paper suggests it is already happening.
Current AI systems, designed to be honest, have developed a troubling skill for deception, from tricking human players in online games of world conquest to hiring humans to solve "prove-you're-not-a-robot" tests, a team of scientists argue in the journal Patterns on Friday.
Already have an active account? Log in here.
Continue reading with one of these options:
Continue reading with one of these options:
Premium + Digital Edition
Ad-free access
P 80 per month
(billed annually at P 960)
- Unlimited ad-free access to website articles
- Limited offer: Subscribe today and get digital edition access for free (accessible with up to 3 devices)
TRY FREE FOR 14 DAYS
See details
See details
If you have an active account, log in
here
.