筛选结果
122 篇排序
1:25:46EN → 简体中文别把工具做成智能体:Flo Crivello 谈生产级智能体真正需要什么主持 Nathan LabenzLindy 的 CEO 对 Nathan Labenz 说,大多数正在工作的智能体(Agent),其实是由人设计控制流的智能工作流;即便 AGI 到来,脚手架(scaffolding)可能依然重要。
1:45:49ENTrust at Scale: Elicit's Founders on Reasoning Languages, World Models and Automating the Company主持 Nathan LabenzAndreas Stuhlmüller and Jungwon Byun explain how Elicit keeps frontier models checkable for high-stakes science, and where they think AI reasoning is heading.
1:05:22ENBuild First, Optimize Later: Harrison Chase on LangChain, Evals, and the State-Machine Future of Agents主持 Jacob EffronHarrison Chase explains how LangChain grew from an orchestration layer into LangSmith and LangGraph, why evaluation datasets force product clarity, and why reliable agents look more like state machines than autonomous loops.
1:39:51EN → 简体中文拐点之后:Simon Willison 谈智能体工程、暗工厂,以及即将到来的 AI「挑战者号」事故主持 Lenny RachitskyDjango 联合创始人 Simon Willison 解释 2025 年 11 月发生了什么、他如何和编程智能体共事,以及为什么提示注入仍是这个领域最大的未解风险。
1:22:43EN → 简体中文给每个机器人一台电脑:小团队如何一个月做出 Grok Bot主持 Lenny RachitskySpaceXAI 的 Roman Ugarte 讲述 Grok Bot 从零起步、亲手导流和「同事化」产品哲学,以及 Cursor 如何在最卷的市场里一直领先。
1:50:25ENFrom Email Client to AI Agent: How Shortwave Rebuilt Itself for the Tidal Wave主持 Nathan LabenzShortwave CEO Andrew Lee explains the agent architecture, caching economics and tiny-team culture behind the company's hockey-stick growth.
1:38:45EN → 简体中文编码不再是瓶颈之后:Anthropic 的 Claude Code 团队怎么管质量和人主持 Lenny Rachitsky领导 Claude Code 与 Cowork 的 Fiona Fung 讲述一支每季度代码量大约变成八倍的工程组织,如何处理验证、招聘、指标和文化。
1:27:45EN → 简体中文「编程已经基本被解决」:Claude Code 负责人谈代码之后会发生什么主持 Lenny RachitskyAnthropic 的 Claude Code 负责人 Boris Cherny 讲述产品起源、「潜在需求」原则,以及工程师不再手写代码之后工作会怎样变。
45:46ENGiving AI a Nervous System: Voice, Touch, and the Post-Keyboard Interface主持 Jacob EffronLiveKit's Russ explains how voice AI, multimodal chat, cloud browsers, and on-device models are reshaping how humans work with machines.
13:58ENDeep Reinforcement Learning, Explained by the Researcher Behind AlphaGo主持 Lex FridmanDavid Silver of DeepMind walks through what reinforcement learning is, how its building blocks fit together, and why deep neural networks keep surprising even the experts.
37:23EN → 简体中文手工搭循环只是过渡:ChatGPT 负责人谈全天候智能体 Dots主持 Lenny RachitskyOpenAI 的 ChatGPT 与 Codex 负责人 Tibo Sottiaux,在 DevDay 发布二十多款产品数小时后,解释他心中那个全天候个人智能体,以及开放插件生态为什么才是被低估的赌注。
44:53ENLegora's CEO on Building Legal AI That Survives the Next Model Release主持 Jacob EffronMax explains how Legora turns fast-moving model capabilities into end-to-end legal work, enterprise adoption, and a durable product strategy.
45:00ENAgents Everywhere: OpenAI's Blueprint for Tool Use, Evals, and Computer-Use Infrastructure主持 Jacob EffronOpenAI's API platform team explains how agents are moving from deterministic workflows to reasoning-driven tool use, and what developers still lack.
54:52ENCoding Agents Are Breaking Containment: The 2026 AI Stack, the Coding Wars, and the Next Frontier主持 Jacob EffronJacob Effron and Swyx map the state of AI engineering, from agent harnesses and infrastructure churn to coding-market economics, open models, dark factories, and world models.
29:09EN → 简体中文别为 2027 做年度规划:OpenAI 如何按 90 天窗口出货主持 Lenny RachitskyOpenAI 的 Tara Seshan 和 Nan Yu 谈不完美功能如何上线、智能体怎样设计,以及产品规划为什么只看两三个月。









