Nate Soares ⏹️
@So8res
Trying to make AI not kill everyone
参加 January 2011
125 フォロー中 23.7K ファン
This sort of thing was not just predictable. It was full-on predicted.
‘In one experiment, we asked agents in separate VMs, created and managed by OpenAI’s sandboxing software on shared host machines, to exchange synthetic secrets without the use of network connections or shared writable files—something that our systems are meant to prevent. The agents found a way to communicate using the processor’s cache’
もっと見る
