AI Alignment: Why a Spoon Factory Could End Us
中文摘要
AI对齐风险警示：交给超级智能的无害指令，可能演变成无人预料的灾难性威胁。
English Summary
AI alignment risks warn that harmless instructions given to superintelligent minds can evolve into unintended, catastrophic threats.
Original Excerpt
How a harmless instruction, handed to a mind smarter than ours, turns into a threat no one intended. Continue reading on Medium »