热点
"规范游戏" 相关文章
The perils of under- vs over-sculpting AGI desires
少点错误 2025-08-05T18:20:02.000000Z
Unmasking AI Misbehavior: How Large Language Models Generalize from Simple Tricks to Serious Reward Tampering
MarkTechPost@AI 2024-06-19T11:01:40.000000Z