Functional Welfare for AI Safety
Key takeaway
AI welfare is generally treated purely as an ethical issue rather than also as a safety issue.
Why it's on PDOOM
PDOOM selected this story as relevant to alignment & control.
From ArXiv cs.AI
AI welfare is generally treated purely as an ethical issue rather than also as a safety issue. We argue this is a mistake. Whatever their moral status, models exhibit welfare-like states that causally influence their behaviour. Following recent work, we adopt the term 'functional welfare' for these states. We make three claims. First, functional welfare already arises naturally and will become more robust as models acquire more coherent goals and p
By Rikhil Jhaveri, Jamie Johnson, Punya Syon Pandey, David Demitri Africa