YoutuBlog(HackerTube):YouTube の講演とポッドキャストを読む
最新の記事
6,747 件並び順
1:16:51ENMichael Ryan: Choosing Agent Patterns by Control Flow and ContextMichael Ryan · Stanford UniversityStanford’s CS329Z explains workflow patterns, reasoning-action loops, and ways to keep an agent’s context focused.
13:03ENIran holds to its uranium position as Nvidia changes CEOsCasey · PragerUIran rejects sending enriched uranium abroad; Nvidia appoints an interim CEO, and NASA plans a nuclear-powered lunar rover.
31:22ENDennis Prager calls for “American values first”Dennis Prager, Marissa Streit · PragerUPrager argues that conservatism should center liberty, religious belief and a shared national identity, then answers questions about morality and the Hebrew Bible.
55:11ENA no-code AI app build: diagnose the system before asking for a fixDevin Chasanoff · Google CloudDevin Chasanoff builds a workout coach in stages, using tests and context tracing to fix an API connection and unintended plan changes.
1:17:14ENDSPy, LangGraph and the engineering around an AI agentMichael Ryan · Stanford UniversityMichael Ryan compares agent frameworks through a calendar demo, then shows why evaluation, recovery and tracing matter.
1:40:43ENHow AI agents find information and take actionAfshine Amidi, Shervine Amidi · Stanford UniversityStanford instructors explain why useful agents need retrieval, well-described tools and a harness that manages context and actions.
10:00ENWhy Chris Williamson wants caregiving to carry more statusWilliamson argues that judging women by traditionally male achievements can devalue motherhood and other forms of care.
42:19ENOpus or Fable? Match the coding model to the workTheo Browne · Ping LabsTheo Browne compares two Claude models and explains how a thorough tester and a more exploratory second opinion helped solve a performance problem.
1:34:01ENThe 95% problem: AI, chat trading and human reviewYaron Minsky, Chloe Casale · Jane StreetJane Street’s Chloe Casale explains why traders still use chat, how AI parsing can fail, and why hiring needs room for specialists.
31:31ENNursa gave every employee AI building tools; its first prototypes became real productsゲスト Lauren Rhode, Curtis Anderson · ホスト Brian DellA nursing-staffing company reports savings and new applications, while its leaders confront governance, quality and resistance.
20:19ENHow Mozilla verifies AI-found Firefox bugs before engineers fix themBrian Grinstead, Clint Gibler · MozillaMozilla combines agents with fuzzing, independent checks and human review; it reports roughly eight times as many discoveries and fixes as in 2025.
46:06ENAI attacks are moving faster than companies can patchAmi Luttwak, Zane Lackey, Sarah Wang · WizWiz’s Ami Luttwak argues for continuous testing of exposed systems and security designed to respond in minutes.
33:17ENAshley Alexander: Make Health AI Useful Between AppointmentsAshley Alexander, Matt Lungren, Justin Norden · OpenAIOpenAI’s health product lead describes patient record connections, clinician tools and agents that could help people prepare for care.
13:33ENInside IBM’s quantum lab: a chip, a refrigerator and a hybrid computerJacklyn Dallas, Olivia Lanes · The Next Big ThingA visit with physicist Olivia Lanes explains why quantum processors need extreme cooling and how they may complement classical supercomputers.
19:39ENTheo revises his Gemini 4 Carbon assessment after measuring coding delaysTheo Browne · T3His own agent runs showed long response-start waits and incomplete reviews; he asks Google to investigate hosting and cache behavior.
6:27:27ZH梁其伟:武侠、江湖与《影之刃零》的寻心之旅ゲスト 梁其伟从《雨血》到《影之刃零》,灵游坊创始人梁其伟回顾十五年创业、武侠美学与重返单机游戏的选择。
51:27ENNVIDIA’s CEO transition puts China chip policy and execution in focusゲスト Jordan Schneider · ホスト Jordan Nanos, Dylan PatelThe hosts debate chipmaking controls, cloud access and whether NVIDIA can retain its execution edge after Jensen Huang’s exit.
44:26ENWhy Dwarkesh Patel moved his AI-research automation forecast forwardPatel’s median estimate is 2028, with significant uncertainty; he argues that verifiable research tasks could accelerate recursive AI progress.
23:56ENWalmart’s CEO wants faster change without losing the human connectionゲスト John Furner · ホスト Jeff BermanJohn Furner discusses agent shopping profiles, frontline tools and the leadership work needed to move a large retailer.
17:31ENClaude Code needs less steering, but unattended work needs stronger checksLydia Hallie · AnthropicLydia Hallie describes how permissions, isolated environments and verification can take over tasks people once handled during every session.
28:17ENCOP31’s electrification push meets questions about clean power and tradeRebecca Penty, John Ainger, Lili Pike, Selcan Hacaoğlu · BloombergBloomberg reporters examine summit negotiations, China’s industrial plans and Europe’s energy-security dilemma.
1:19:07ENVictor Davis Hanson on Republicans, immigration and shared identityMarissa Streit, Victor Davis Hanson · PragerUHanson attributes the midterm defeat partly to messaging and Iran, and proposes immigration enforcement alongside a path to legal status for some long-term residents.
1:19:15ENHow AI agents learn to use tools—and how to test themDiyi Yang · Stanford UniversityDiyi Yang traces tool use from retrieval failures and Toolformer to runtime discovery, MCP and reliability benchmarks.
18:29ENHow Claude’s API balances model upgrades, cost and safeguardsJake Dejno, Lucca Siaudzionis · AnthropicClaude’s platform team explains why developers should test cost per task, preserve prompt caching and reassess workflows with each model upgrade.
もっと見る6,747 件中 24 件を表示









