[人人能懂] 从“大力出奇迹”到“四两拨千斤”

AI可可AI生活 · Sep 8, 2025 · 25m

00:00:30 给AI请个“速记员”，效率提升30倍

00:04:57 AI为啥爱“猜答案”？这事儿得从考试说起

00:10:14 高手过招：为什么说“三次”探索胜过“两次”？

00:15:23 AI训练场上的老司机，如何做到油门收放自如？

00:19:24 不懂代码？没关系，AI帮你组建一个技术团队

本期介绍的几篇论文：

[CL] REFRAG: Rethinking RAG based Decoding

[Meta Superintelligence Labs & National University of Singapore]

https://arxiv.org/abs/2509.01092

---

[LG] Why Language Models Hallucinate

[OpenAI]

https://cdn.openai.com/pdf/d04913be-3f6f-4d2b-b283-ff432ef4aaa5/why-language-models-hallucinate.pdf

---

[LG] When three experiments are better than two: Avoiding intractable correlated aleatoric uncertainty by leveraging a novel bias--variance…