YoutuBlog (HackerTube): read YouTube talks and podcasts

Recently updated channels

Pick one to see only that channelBrowse all channels →

Latest articles

6,152 articles
Sort
3 slides15:28EN
AI Engineer· Nov 9, 2026Ryan Carson: One manager agent coordinates 20 coding agentsRyan Carson · UntangleUntangle delegates coding, review and merge coordination to agents, but its founder watches each feature before approving shipment.Agent orchestrationCoding agentsDeveloper workflows & testing+2
4 slides1:50:34EN
AI Engineer· Nov 9, 2026A financial AI agent must show its workFrancesco Galletta, Felippe Felisola Caso · MonzoA wedding-budget demo pairs tested calculations with evidence, decision gates and independent checks.Harness engineeringAI agentsPersonal Finance+2
8 slides19:50EN
AI Engineer· Nov 9, 2026Keiji Kanazawa rebuilt his agent system after reading its codeKeiji Kanazawa · MicrosoftA three-week refactor produced fake agents and expensive tests. He rebuilt around explicit goals and evaluations.Coding agentsEvalsAgent engineering+2
4 slides20:51EN
AI Engineer· Nov 9, 2026Jason Mancuso: Scaling agent reinforcement learning across mixed GPUsJason Mancuso · ModalModal combines asynchronous rollouts, mismatch corrections and compressed weight updates to train coding agents across a fragmented GPU fleet.Agent engineeringModels & trainingInfrastructure & deployment
4 slides24:47EN
How I AI· Nov 9, 2026PodcastClaire Vo: Fable 5.2 excels at creative builds, but not every designA marketing animation, furniture guide and 3D typewriter impressed Vo; independently generated website designs did not.Foundation ModelsCoding agentsGenerative media+2
4 slides24:18EN
Matthew Berman· Nov 9, 2026Fable 5.2 built playable demos—but several cost thousandsMatthew Berman · Forward FutureMatthew Berman shows games, creative software and simulations, with estimated API costs from $25 to $15,000.Coding agentsFoundation ModelsAI cost & performance+2
7 slides18:32EN
AI Engineer· Nov 8, 2026Why a plausible contract analysis missed $800,000Natalia Connolly, Kevin Madura · AlixPartnersAlixPartners’ Natalia Connolly and Kevin Madura show how missing links, renewal clauses and silent access errors can derail an AI procurement analysis.Agent engineeringEnterprise AIData quality & curation+1
3 slides23:15EN
Latent Space· Nov 8, 2026Podcast · 2 speakersJay Parikh: GitHub must adapt as coding agents change developmentGuest Jay Parikh · Host Shawn WangGitHub's scale, model choices and security are changing as agents join developers, says Microsoft CoreAI's Jay Parikh.Coding agentsDeveloper workflows & testingInfrastructure & deployment+2
58:33EN
Lenny's Podcast· Nov 8, 2026Podcast · 2 speakersGemini’s product chief on testing models and building ahead of themGuest Tulsee Doshi · Host Lenny RachitskyTulsee Doshi explains a small-eval starting point, her 60-20-20 product framework and why model behavior itself is a user experience.Product ManagementFoundation ModelsEvals+2
46:40EN
Peter Yang· Nov 8, 2026Podcast · 2 speakersAshley Alexander: How AI Helps Me Care for My Parents With CancerGuest Ashley Alexander · Host Peter YangA caregiver uses AI to prepare for appointments, organize records and ask better questions—while keeping doctors at the center of treatment.AI in healthcareHuman-AI CollaborationProductivity
12:38EN
Chris Williamson· Nov 8, 2026Podcast · 2 speakersWhat makes AI-generated work feel like slop?Host Chris WilliamsonChris Williamson and his guest ask creators to explain their judgments, and to distinguish a tool’s defaults from intentional craft.CreativityGenerative mediaHuman-AI Collaboration
6 slides18:56EN
AI Engineer· Nov 8, 2026How Citadel Securities builds a memory that catches troubled projectsJoao Wenzel · Citadel SecuritiesJoao Wenzel describes an agent system that weighs evidence, tracks aging facts and tests its warnings against what happened next.Agent engineeringEnterprise AIEvals+2
7 slides18:39EN
AI Engineer· Nov 8, 2026How Ramp tests a bookkeeping agent before and after launchRyan Stevens · RampRyan Stevens explains synthetic businesses, all-or-nothing scoring, skill ablation and a two-period test for agent memory.EvalsAgent engineeringEnterprise AI
5 slides16:09EN
AI Engineer· Nov 8, 2026How Range’s financial planners built their own AI workflowsMatt Ragone · RangeMatt Ragone’s team used real cases and existing advice standards to build skills, while keeping a certified planner’s review before client delivery.Agent engineeringEnterprise AIWorkflow automation+1
6 slides20:28EN
AI Engineer· Nov 8, 2026Why AI coding gains depend on more than faster code generationMartin Harrysson, Prakhar Dixit · McKinseyMcKinsey speakers describe smaller teams, shorter loops, curated context and quality checks observed among enterprise clients.Developer productivityAgent engineeringSoftware engineering+1
6 slides1:21:42EN
Y Combinator· Nov 8, 2026What AI biology can do now, from cancer data to DNA designAlfredo Gonzalez, Yusuf Roohani, Garyk Brixi, Divya NoriFour researchers explain patient-specific cancer analysis, virtual cells and genome models, separating early experiments from proposed clinical applications.AI for scienceDrug DiscoveryFoundation Models+1
3 slides31:22EN
AI Engineer· Nov 7, 2026Nouha Dziri on Making Coding-Agent Teams More Cost-EfficientNouha Dziri · CohereExperiments on ProgramBench and Commit0 show why the task bottleneck, lead model and coordination design matter more than simply adding agents.Multi-agent systemsCoding agentsAgent orchestration+2
2 slides20:08EN
Matthew Berman· Nov 7, 2026METR Finds Faster AI Research at Anthropic, With Major UncertaintyMatthew Berman · Forward FutureMatthew Berman examines an independent assessment of AI-assisted R&D and the limits on its access to evidence.AI researchAI SafetyEvals+1
3 slides19:34EN
AI Engineer· Nov 7, 2026How Cloud Agents Help Review Changes to a Security MasterAmol Kapoor, Clifford Ressel · Nori AgenticAmol Kapoor and Clifford Ressel explain why private-asset data is difficult to reconcile and how an agent assists human reviewers.AI in financeData quality & curationAgent engineering+2
57:17EN
20VC with Harry Stebbings· Nov 7, 2026Podcast · 2 speakersScott Wilson on WashU’s Endowment, Concentration and Co-InvestingGuest Scott Wilson · Host Harry StebbingsWashU’s CIO explains its manager relationships, direct investments, liquidity constraints and views on private-market valuations.InvestingVenture CapitalDecision Making+2
4 slides13:27EN
AI Engineer· Nov 7, 2026A Financial Agent Must Show How It Reached Its DecisionAnirudh Veeraragavan · FieldguideAnirudh Veeraragavan uses a bank reconciliation to show how to make an agent’s work reviewable.Agent engineeringEvalsSafety & governance
18:09EN
PragerU· Nov 7, 2026Owen Anderson Discusses His ASU Training LawsuitShabbos Kestenbaum, Owen Anderson · PragerUThe professor describes his challenge to diversity training and a separate dispute over his courses; ASU disputes his discrimination allegations.EducationFree SpeechReligion+1
4 slides17:35EN
AI Engineer· Nov 7, 2026Agent Infrastructure Needs Persistent State and Elastic ComputeAkshat Bubna · ModalModal CTO Akshat Bubna explains how sandboxes, shared storage and network controls support agents at scale.Sandboxes & isolationAgent engineeringInfrastructure & deployment+1
1:26:17EN
Cognitive Revolution "How AI Changes Everything"· Nov 7, 2026Podcast · 5 speakersAI Forecasts, GPU Markets and the Question of What to BuildGuest Brian Zhou, Mike San Miguel, Bryan Bischof · Host Nathan Labenz, Prakash NarayananNathan Labenz and Prakash Narayanan examine AI acceleration through election forecasting, compute trading and venture research.AI researchEvalsInfrastructure & deployment+2
Load moreShowing 24 of 6,152