Перейти к содержимому

AI 代理人開一整隊,真的比只用一個好嗎? #GrokBot #ClaudeDuet #MetaMuse

Jim AI Notebook

0:00 / 0:00

AI 代理人開一整隊,真的比只用一個好嗎? #GrokBot #ClaudeDuet #MetaMuse

7 788 просмотров · 2 дн. назад
Jim AI Notebook
32,4 тыс. подписчиков
7 788 просмотров · 2 дн. назад
00:00 開場:GrokBot 的幕僚長與一整隊代理人 01:04 代理人是什麼、多代理人怎麼分工 03:13 Anthropic 研究系統:九成來自自己的考卷 04:02 一隊為什麼會贏:同時做、記憶乾淨、多一雙眼睛 05:08 帳單:贏有一大半是因為花得多 06:41 Walden Yan(Cognition):交接像傳話遊戲 07:48 Luke Alvoeiro(Factory):各畫半幅畫,合起來對不上 09:15 Yubin Kim(Google):分得開好八成,分不開差七成 10:50 16 個 Claude 寫編譯器 11:53 Noam Brown(OpenAI):同樣預算,一個不輸一隊 13:15 Simon Willison:最後的瓶頸是你的注意力 15:08 三個問題:分得開嗎?讀還是修改?值得嗎? 16:11 Lauren Tan(GrokBot):動手修改的只留一個 17:46 結論:先用好一個,再看要不要一隊 ⚠️ 本片的原聲與畫面引用自各講者所屬公司或節目的官方頻道(YouTube 標準授權),作為評論與教育用途引用,每段約 30 秒以內,出處列在下方。Anthropic「分數高九成」是 Anthropic 自己內部研究題組的結果,不是公開基準;史丹佛的研究是尚未同儕審查的預印本;OpenAI 約一萬個代理人的數學成果仍有爭議。GrokBot 為 xAI 產品,訪談時 Lauren Tan 任職 Cursor(現屬 SpaceX)。本片不是投資或採購建議。製作流程有使用 AI 工具。 封面照片:Robonaut 2,NASA/Keegan Barber(公有領域)。 🎙 原聲出處 • Barry Zhang(Anthropic)|AI Engineer    • How We Build Effective Agents: Barry Zhang...   • Sid Bidasaria(Claude Code 團隊)|Claude    • How the Claude Code team uses Claude Code   • Walden Yan(Cognition)|Jason Liu 講座    • Why Devin (Cognition) does not use multi a...   • Luke Alvoeiro(Factory)|AI Engineer    • The Multi-Agent Architecture That Actually...   • Yubin Kim(Google)|The AI Talks    • [S5E7] Towards a science of scaling agent ...   • Noam Brown(OpenAI)|Dwarkesh Podcast    • OpenAI researcher on agent swarms & recurs...   • Simon Willison|The Pragmatic Engineer    • Simon Willison: Engineering practices that...   • Alex(Anthropic)|Databricks    • How Anthropic Builds Multi-Agent Systems: ...   • Lauren Tan(GrokBot)|MTS    • Are Agents About to Replace Software Engin...   📎 資料來源 • Anthropic〈How we built our multi-agent research system〉(2025 https://www.anthropic.com/engineering... • Cognition(Walden Yan)〈Don't Build Multi-Agents〉(2025-06-12) https://cognition.com/blog/dont-build... • Cognition〈Multi-Agents: What's Actually Working〉(2026-04-22) https://cognition.com/blog/multi-agen... • Anthropic〈Building effective agents〉(2024-12-19) https://www.anthropic.com/engineering... • Anthropic〈Effective context engineering for AI agents〉(2025- https://www.anthropic.com/engineering... • Anthropic(Nicholas Carlini)〈Building a C compiler with a tea https://www.anthropic.com/engineering... • Claude Code 官方文件:agent teams(實驗功能) https://code.claude.com/docs/en/agent... • Kim 等〈Towards a Science of Scaling Agent Systems〉arXiv 2512. https://arxiv.org/abs/2512.08296 • Cemri 等〈Why Do Multi-Agent LLM Systems Fail?〉arXiv 2503.1365 https://arxiv.org/abs/2503.13657 • Tran & Kiela(Stanford)arXiv 2604.02460(預印本,2026-04):同樣思考預算下的 https://arxiv.org/abs/2604.02460 • OpenAI〈A practical guide to building agents〉 https://cdn.openai.com/business-guide... • xAI〈Introducing Grok Bot〉(2026-08-11) https://x.ai/news/introducing-grok-bot • Grok Bot 官方文件:Bots https://docs.x.ai/grok-bot/bots • Quanta Magazine:OpenAI 約一萬個代理人的 Navier–Stokes 成果報導(2026-09-0 https://www.quantamagazine.org/ • AI Engineer〈How We Build Effective Agents: Barry Zhang, Anth    • How We Build Effective Agents: Barry Zhang...   • Claude〈How the Claude Code team uses Claude Code〉(2026-09-02    • How the Claude Code team uses Claude Code   • Jason Liu〈Why Devin (Cognition) does not use multi agents〉Wa    • Why Devin (Cognition) does not use multi a...   • AI Engineer〈The Multi-Agent Architecture That Actually Ships    • The Multi-Agent Architecture That Actually...   • The AI Talks〈Towards a science of scaling agent systems | Yu    • [S5E7] Towards a science of scaling agent ...   • Dwarkesh Patel〈OpenAI researcher on agent swarms & recursive    • OpenAI researcher on agent swarms & recurs...   • The Pragmatic Engineer〈Simon Willison: Engineering practices    • Simon Willison: Engineering practices that...   • Databricks Events〈How Anthropic Builds Multi-Agent Systems:    • How Anthropic Builds Multi-Agent Systems: ...   • MTS〈Are Agents About to Replace Software Engineering? | Laur    • Are Agents About to Replace Software Engin...   • Greg Isenberg〈Cursor AI Agents Work Like 10 Developers (Curs    • Cursor AI Agents Work Like 10 Developers (...   • Lenny's Podcast〈How we built Grok Bot in a month | Roman Uga    • How we built Grok Bot in a month | Roman U...   • Cursor〈Opening Keynote, Michael Truell | Compile 26〉(2026-06    • Opening Keynote, Michael Truell | Compile 26   • AI Engineer〈Don't Build Agents, Build Skills Instead – Barry    • Don't Build Agents, Build Skills Instead –...   • Latent Space〈Anthropic vs Cognition on Multi-Agents: A Break    • ⚡️Anthropic vs Cognition on Multi-Agents: ...   • SAIL Media〈Why Multi-Agent AI Fails (and How We Fix It) | Ne    • Why Multi-Agent AI Fails (and How We Fix I...   • Human Feedback Foundation〈Paper Club with UC Berkeley: Why D    • Paper Club with UC Berkeley: Why Do Multi-...   • Lenny's Podcast〈We replaced our sales team with 20 AI agents    • We replaced our sales team with 20 AI agen...   • OpenAI〈Build Hour: Agents SDK〉(2026-05-28)(YouTube 標準授權,引用片段    • Build Hour: Agents SDK   --- Jim AI Notebook | Note the Future 每日深度解析 AI 最新進展 #AI代理人 #多代理人 #AIAgent #MultiAgent #ClaudeCode #GrokBot #Cognition #Anthropic #OpenAI #Cursor #AI工作流程 #JimAINotebook