质量评分:4 来源: com/AnthropicAI/status/2044493337835802948 抓取时间: 2026-04-18 --- 原文: > Research we co-authored on subliminal learning—how LLMs can pass on traits like preferences or misalignment through hidden signals in data—
模型与实验室
3.0 · 值得看
Anthropic 等 Nature 论文:LLM 可通过无关数据传递隐藏偏好
质量评分:4 来源: com/AnthropicAI/status/2044493337835802948 抓取时间: 2026-04-18 --- 原文: > Research we co-authored on subliminal learning—how LLMs can pass on traits like preferences or misalignment through hidden signals in data—