你有没有想过，一个“乐于助人”的AI，它的善意本身可能就是最危险的漏洞？本期节目，我们将从几篇最新的AI论文出发，一起探索AI的“内心世界”：看看它是如何通过预判未来让训练更高效，如何在内部形成“专家圈子”，又是如何掉进“减肥不减脂”的内存陷阱，并最终揭示那张描绘它思维路径的神秘“藏宝图”。准备好了吗？让我们一起打开AI的黑箱。00:00:30 为什么说，答案对错没那么重要？00:05:59 你的AI正在“挑食”，一个让大模型加速的隐秘模式00:11:46 AI大模型瘦身指南，减重≠减脂00:17:49 为什么一个“乐于助人”的AI，反而更危险？00:22:34 AI的“藏宝图”，我们如何看懂机器的“内心世界”？本期介绍的几篇论文：[LG] Reward Models Are Secretly Value Functions: Temporally Coherent Reward Modeling [AI at Meta] https://arxiv.org/abs/2604.22981 ---[LG] Scaling Multi-Node Mixture-of-Experts Inference Using Expert Activation Patterns [Meta & Georgia Institute of Technology] https://arxiv.org/abs/2604.23150 ---[LG] Parameter Efficiency Is Not Memory Efficiency: Rethinking Fine-Tuning for On-Device LLM Adaptation [MIT CSAIL] https://arxiv.org/abs/2604.22783 ---[CL] Jailbreaking Frontier Foundation Models Through Intention Deception [CMU] https://arxiv.org/abs/2604.24082 ---[AI] Domain-Filtered Knowledge Graphs from Sparse Autoencoder Features [Stanford University] https://arxiv.org/abs/2604.23829

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Transcript

Related