Is sandboxing sufficient to contain rogue agents?

What happened

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…

Summary assembled by rule from the sources below

Timeline

1. 03:27
   First appeared on Hacker NewsHHacker News
2. 12:16
   Discussion started on LobstersLLobsters

Sources