2 papers
cs.CY2026
Position: We Need Large Language Models Optimized For Our Well-Being
Ashton Anderson, Harsh Kumar, Louis Tay +1
Large language models are useful because we taught them to give us what we want. This works when success can be judged immediately, but people increasingly bring these systems thei…
cs.CY2026
Diagnosing and Repairing Persona Collapse in LLM Advice
Harsh Kumar, Karina Vold, Louis Tay +1
LLMs are increasingly used for personal advice on relationships, work, moral dilemmas, and crises. Post-training selects a stable, prosocial Assistant persona, but good advice requ…