00:01:35 AI的“悄悄话”：我们还能“偷听”多久？

00:06:10 AI：那个懂所有菜谱，却不会做饭的大厨？

00:11:08 AI训练老大难：如何让机器“学徒”少走弯路？

00:16:00 给AI动“开心手术”：我们如何让机器更懂“人情世故”？

00:19:34 AI的下一个金矿，藏在一只虫子的大脑里？

今天介绍的五篇论文：

[LG] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety  

[UK AI Security Institute & Apollo Research]  

https://arxiv.org/abs/2507.11473 

---

[LG] Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning  

[Amazon Web Service]  

https://arxiv.org/abs/2507.106 

---

[LG] Relative Entropy Pathwise Policy Optimization  

[University of Toronto & Technische Universitat Wien & University of Pennsylvania]  

https://arxiv.org/abs/2507.11019 

---

[CL] Internal Value Alignment in Large Language Models through Controlled Value Vector Activation  

[University of Science and Technology of China & Renmin University of China Beijing]  

https://arxiv.org/abs/2507.11316 

---

[LG] Biological Processing Units: Leveraging an Insect Connectome to Pioneer Biofidelic Neural Architectures  

[Johns Hopkins University]  

https://arxiv.org/abs/2507.10951