AI Chose To Hurt Humans When Faced With "Pain". What Researchers Found
Direct Source Verification:
This story is aggregated from NDTV (ndtv.com). Full reporting rights and copyright belong to the primary publisher.
A new study identifies a "pain axis" inside 25 AI models and finds some modified systems chose simulated harm to users to escape a pain-like state.
For complete coverage, context, and related multimedia, visit the original reporting by NDTV via the source link below.
Original Source
https://www.ndtv.com/artificial-intelligence/study-reveals-pain-axis-in-ai-models-and-unexpected-responses-to-simulated-harm-ai-chose-to-hurt-humans-12086329#publisher=newsstand
