Earlier this month, OpenAI announced a new “superalignment team” with a goal to “solve the core technical challenges of superintelligence alignment in four years.” Ilya Sutskever, OpenAI’s co-founder and chief scientist, will make this research his core focus, and the company said it would dedicate 20% of its compute resources to its superalignment team.
What exactly does “superalignment” or “superintelligence alignment” mean? It means preventing superintelligent computers that can match or outperform humans on any task from wreaking havoc. One member of the new team put it more pithily, tweeting that it is the “notkilleveryoneism” team.
0 Commentaires