A theoretically grounded science of capable agents could inform AI safety and sentience criteria

aran_nayebi · x · 2026-09-29

In the final part of a thread, researcher Aran Nayebi argues that if successful, this work would yield a theoretically supported science of capable agents—providing important guarantees for AI safety and possibly isolating formal criteria for when and why a system could be deemed sentient. Only the 4/4 segment of the thread is included here.

Original post →

More from Safety

Safety channel →