MIT study finds AI doesn’t, in fact, have values // Tech Crunch
Researchers at MIT have found that AI systems do not develop “value systems” over time. “For me, my biggest takeaway from doing all this research is to now have an understanding of models as not really being systems that have some sort of stable, coherent set of beliefs and preferences,” says graduate student Stephen Casper. “Instead, they are imitators deep down who do all sorts of confabulation and say all sorts of frivolous things.”
|