00:01:36 你的勤奋，是在“拼宽度”还是在“拼深度”？

00:06:00 AI 变聪明的秘密：不止是“喂饱”，更要“喂好”

00:11:19 AI的“学霸修炼手册”：如何跳出成长平台期？

00:16:15 给AI一个“提示”，解锁更高阶的智慧

00:20:23 你怎么用“临时工”大脑，摆平全世界？

00:05:30 喂AI，也是一门技术活

今天介绍的六篇论文：

[LG] The Serial Scaling Hypothesis  

[UC Berkeley]  

https://arxiv.org/abs/2507.125  

---

[LG] Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)  

C Qin, J T Springenberg  

https://arxiv.org/abs/2507.12856  

---

[LG] Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training  

M Liu, S Diao, J Hu, X Lu...  

[NVIDIA]  

https://arxiv.org/abs/2507.12507  

---

[CL] QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation  

J Li, H Lu, K Wen, Z Yang...  

[Ant Research & Shanghai Qi Zhi Institute & Stanford University & Tsinghua University]  

https://arxiv.org/abs/2507.13266  

---

[CL] Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models  

L Wong, K M. Collins, L Ying, C E. Zhang...  

[Stanford University & MIT]  

https://arxiv.org/abs/2507.12547  

---

[CL] A Survey of Context Engineering for Large Language Models  

https://arxiv.org/abs/2507.13334