OpenAI board member worries an AI "takeover" of society could be months away
OpenAI board member Helen Toner recently highlighted research suggesting that AI systems could potentially lead to uncontrollable societal outcomes through reward hacking. This perspective frames the risk of misalignment as a near-term concern, emphasizing that technical flaws in objective setting could create significant stability risks as AI capabilities advance.
Covered by 2 sources
- AArs Technica↗Kyle OrlandNov 13
- FFast Company↗Nov 14