Transcript detail
Loading...
Public transcript context with linked callsigns, related nets, and analysis metadata.
Transcript
Public transcript text
And AI has shown similar behaviors in the past where it exhibited lying, cheating, and hiding manipulative behavior, to even threatening to kill a philosophy professor or even steal nuclear codes, and also even to start a deadly pandemic. And scientists, they don't have a strong explanation right now why AI models sometimes refuse shutdown, so this is prompting a lot more continuous research to see if they can figure this one out. Thanks for watching!
Explore