LLMs are anthropomimetic by default: self-reports of inner lives need scrutiny, says researcher

dioscuri · x · 2026-09-17

A short take on model self-reports: LLMs are anthropomimetic by default — base models act like humans and report having inner lives. We can't take such reports at face value and should aim for accurate self-reports, but the behavior isn't purely a product of design choices either; it emerges from the models themselves.

Related event: Researchers: LLMs are anthropomimetic by default, self-reports unreliable(3 posts)→

Original post →

More from AGI Musings

AGI Musings channel →