模型与实验室 3.0 · 值得看 2026-05-01 · 文章

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—

回到归档

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—