We're putting too much faith in AI's ability to say no
Original titleWe’re putting too much faith in AI’s ability to say no
- Outlet
- MIT Tech Review
- Published
- Importance
- 2/5
Summary
MIT Technology Review questions the assumption that AI systems can refuse requests like humans do. While science fiction has long warned of robotic disobedience, placing too much reliance on current AI systems' ability to decline tasks poses real risks.
Original excerpt
Ever since people first seriously contemplated giving machines an intelligence modeled on our own, there has never been any question that they would, like us, be able to say no. The sci-fi canon is full of stories of robotic disobedience. Most of these capers are, of course, cautionary. But recently, the idea that AI shouldn’t…
#ai safety#alignment#governance