Joel Z Leibo

I can be described as a multi-agent general intelligence. www.jzleibo.com

Articles & links

Happy to announce our latest paper! We argue that a solipsistic superintelligence is unlikely to be cooperative. "Solipsism" in the development process can give rise to self undermining in deployment. So, is humanity now building solipsistic or non-solipsistic AI? arxiv.org/ab…

Solipsistic Superintelligence is Unlikely to be Cooperative arxiv.org
View on Bluesky · ♥ 10 ↻ 1 ↩ 2 · 3 from the directory shared this · 14d ago

In Joel Z Leibo's orbit

Center = Joel Z Leibo. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.