본문으로 건너뛰기

#Alignment Drift

3개의 포스트

[논문리뷰] SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement

댓글 수 로딩 중

[논문리뷰] The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies

댓글 수 로딩 중

[논문리뷰] TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs

댓글 수 로딩 중