Is sandboxing sufficient to contain rogue agents?

发生了什么

Quick caveats: this is a post on AI safety, written by a cryptography professor. If that troubles you, you should read something else. I try hard not to work on AI (except when the topic occasional…

摘要按规则整理自下方来源原文

时间线

1. 03:27
   Hacker News 最先出现HHacker News
2. 12:16
   Lobsters 出现讨论LLobsters

来源