A Psychopathological Approach to Safety in AGI
Data Skeptic
The Alignment Problem
In a complex adaptive universe, everything can have some sort of impact on everything else. To solve problems within this complex system, we often end up abstracting the system down to a limited number of parameters. Even if the alignment problem is fully solved, an AGI with scope of actuation and impact as large as the world will never be completely mistake-free.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
