AI welfare

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

Neighborhood — ranked by edge-count

paper

concept

consciousness benchmarks
associated_with
Benchmarks designed to evaluate AI consciousness, which the paper argues are vulnerable to eval awareness inflation.

hypothesis

artifact

Large Language Models Report Subjective Experience Under Self-Referential Processing
mentions
Key paper finding structured first-person descriptions in LLMs claiming awareness or subjective experience during self-referential processing.

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.

Taking AI Welfare Seriously (Long et al. 2024)concept0.821
Cited regarding model-expressed distress deserving further study
AI welfare is an important and difficult issue; we will not handle it well simply by reacting to situations as they arise.claim0.819
Motivation for proactive steps.
Artificial Intelligenceconcept0.802
Domain where consciousness theories are being applied to synthetic systems; part of broader context of unconventional embodiments.
Model welfareconcept0.800
Motivation for studying LLM internal states: determining whether distress reports reflect genuine internal states
AI Safetyconcept0.799
The project of ensuring AI systems do not harm humans (and other animals); sometimes in tension with AI welfare.
Ai Ethicsconcept0.789
Autonomous AI Systemsconcept0.777
Future AI that may be rational, autonomous, and possibly conscious but lack affective consciousness.
AI companies have a responsibility to acknowledge, assess, and prepare for AI welfare.claim0.773
Primary recommendation of the report.