AI welfare protections

Possible protections for LLMs contingent on identifying entities that may be moral patients

Neighborhood — ranked by edge-count

paper

concept

AI welfare
related_to
The field concerned with the wellbeing of AI systems, which the paper says must consider benchmark reliability issues from eval awareness.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

AI Safetyconcept0.781
The project of ensuring AI systems do not harm humans (and other animals); sometimes in tension with AI welfare.
AI welfare is an important and difficult issue; we will not handle it well simply by reacting to situations as they arise.claim0.778
Motivation for proactive steps.
Taking AI Welfare Seriously (Long et al. 2024)concept0.775
Cited regarding model-expressed distress deserving further study
Ai Ethicsconcept0.758
AI companies have a responsibility to acknowledge, assess, and prepare for AI welfare.claim0.755
Primary recommendation of the report.
The risk of under-attribution of AI welfare appears to be both reasonably likely and reasonably harmful.claim0.738
Key motivation for precautionary action.
AI companies should immediately hire or appoint an AI welfare officer.claim0.731
First structural step recommended.
Model welfareconcept0.726
Motivation for studying LLM internal states: determining whether distress reports reflect genuine internal states