American AI safety researcher and philosopher — Research Analyst at Open Philanthropy — who writes long-form philosophical analysis of AI risk, alignment, and related questions with unusual rigor.
Creates the most philosophically rigorous analysis of AI power-seeking risk — Carlsmith's Is Power-Seeking AI an Existential Risk? is the most careful probabilistic argument for AI risk as a serious concern, engaging honestly with uncertainty rather than asserting certainty.
Discussing
Ask anything about Joe Carlsmith — their ideas, influences, contradictions, legacy.
Sign in to start a conversation.