![[人人能懂] 给AI装上测谎仪、传送门和贴身家教](https://image.xyzcdn.net/FuDP4HpAp8ezgVZMmEel3mblKCmJ.jpg@small)
109
0你有没有想过，AI也会“生病”、“开窍”和“自我反省”？本期节目，我们将一口气解锁五篇最新论文，带你看看科学家们如何像高明的医生和顶级的教练一样，深入AI的“内心世界”。我们将一起探索：如何给AI装上“测谎仪”，精准诊断它胡说八道背后的两种病根；又如何用一个“传送门”把它送到难题的半山腰，让它瞬间开窍；我们还会看到AI如何自己给自己出题、自己教自己，甚至像开了“天眼”一样，一边解题一边复盘。准备好了吗？让我们一起看看AI是如何学会更聪明地思考的。
00:00:31 给AI装个“测谎仪”，需要几步？
00:05:38 AI训练的“传送门”，如何让机器“开窍”？
00:11:26 遇到难题怎么办？先给自己出几道简单的
00:16:48 AI的“稳定”，原来可以又快又好
00:22:15 AI的自我修炼，如何不开天眼，也能洞察天机？
本期介绍的几篇论文：
[LG] HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs
[Virginia Tech & MIT & Dartmouth College]
---
[LG] Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
[FAIR at Meta]
---
[LG] Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
[MIT & Meta FAIR]
---
[LG] LLM-42: Enabling Determinism in LLM Inference with Verified Speculation
[Microsoft Research & University of Washington & Indian Institute of Science]
---
[LG] Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
[Meta & UCLA & HKU]
