Several labs are talking about building superintelligence, but can it be made safe with the tools that we have? What if we had weakly superhuman AGI to help us?
In this talk, Giles Edkins will explore some of the projects, ideas, and counterarguments in the quest to use AI to align AI.
AI Safety Thursdays: Can AI solve its own alignment problem?
Thursday, August 7th, 6:00pm − 9:00pm
Several labs are talking about building superintelligence, but can it be made safe with the tools that we have? What if we had weakly superhuman AGI to help us?
In this talk, Giles Edkins will explore some of the projects, ideas, and counterarguments in the quest to use AI to align AI.