causal
LLM Personality Volatility Threatens Diachronic Responsibility
Because LLMs can have their personalities radically changed by prompting and may lack a stable identity, an extraordinarily attitudinally volatile AI may amount to short-lived time slices rather than a single agent persisting through time, which breaks the background assumption of stable personal identity that responsibility attributions across time normally depend upon.
causalpending
Speaker
Christian ListEvidence Quote
“agency and responsibility is also a kind of forensic accounting device in order to be able to make stable action attributions across time... if you have an AI technology that is extraordinarily attitudinally volatile, then maybe you just have these very short-lived time slices and those are the kind of meaningful units of agency... that completely breaks our normal moral understandings of agency and responsibility.”
Created: 6/13/2026, 12:28:26 AM
Your notes
Loading notes...