EPISODE · Oct 14, 2025 · 29 MIN
[人人能懂] 从攻防博弈、意念注入到思维诊断
from AI可可AI生活
你有没有想过,在AI安全的攻防战中,为什么防御者总是慢半拍?我们能否跳过对话,直接把指令“注入”AI的大脑?在众多复杂的AI模型背后,是否存在一个统一所有武功的“心法总纲”?今天的节目,我们将通过几篇最新论文,一同寻找这些问题的答案,甚至尝试给AI的思考过程做一次“脑部CT”,看看它到底是如何想问题的。00:00:32 AI安全的“纸上谈兵”:为什么说攻击者总是后出手的那个?00:05:36 AI的“意念注入”:如何把指令直接写进模型大脑?00:11:22 AI大模型的心法:一个统一所有武功的“总纲”00:18:58 给大模型装上导航,能不能开得更快?00:23:38 给AI做个脑CT:看清它思考的脉络本期介绍的几篇论文:[LG] The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against LLM Jailbreaks and Prompt Injections[OpenAI & Anthropic & Google DeepMind]https://arxiv.org/abs/2510.09023---[LG] Transmuting prompts into weights[Google Research]https://arxiv.org/abs/2510.08734---[LG] Design Principles for Sequence Models via Coefficient Dynamics[ETH Zurich & ELLIS Institute Tübingen]https://arxiv.org/abs/2510.09389---[LG] The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton[Harvard University]https://arxiv.org/abs/2510.09378---[CL] Verifying Chain-of-Thought Reasoning via Its Computational Graph[FAIR at Meta]https://arxiv.org/abs/2510.09312在小宇宙查看该单集文稿
Embed this episode
NOW PLAYING
[人人能懂] 从攻防博弈、意念注入到思维诊断
No transcript for this episode yet
Similar Episodes
No similar episodes found.