Kürzlich aktualisierte Kanäle

Wählen, um nur diesen Kanal zu sehenAlle Kanäle →

Ergebnisse

9 Artikel
Sortieren
1:03:05EN
20VC with Harry Stebbings· 17. Okt. 2026Podcast · 2 StimmenHarrison Chase on Building Reliable Agents, Model Routing and MemoryGast: Harrison Chase · Moderation: Harry StebbingsThe LangChain co-founder explains why agents remain difficult to control, where domain expertise matters, and how his team manages coding-agent costs.AI agentsAgent orchestrationEvals+2
1:19:54EN
20VC with Harry Stebbings· 19. Sept. 2026Podcast · 2 StimmenThomas Sohmers on AI Inference, Memory and Data-Center GrowthGast: Thomas Sohmers · Moderation: Harry StebbingsPositron’s co-founder discusses the engineering economics of inference, his views on AI infrastructure and regulation, and the risks he sees in financing and concentration.InferenceSemiconductorsAI cost & performance+2
1:06:31EN
No Priors: AI, Machine Learning, Tech, & Startups· 20. März 2026Podcast · 2 StimmenAndrej Karpathy Hasn't Typed a Line of Code Since DecemberModeration: Sarah Guo, Elad GilOn No Priors, the OpenAI cofounder and former Tesla AI director describes the loopy era of coding agents, AutoResearch, and why the bottleneck is now the human.Coding-AgentenAutoresearchAgent orchestration+3
36:58EN
No Priors: AI, Machine Learning, Tech, & Startups· 9. Okt. 2025Podcast · 2 StimmenSTaR's Author Wants Models With EQ, Not Just More IQModeration: Sarah Guo, Elad GilEric Zelikman, the Stanford and xAI researcher behind STaR and Quiet-STaR, launches humans& on the bet that three years of IQ scaling left models emotionally unintelligent.Modelle & TrainingPost-trainingReinforcement Learning+3
4 Folien16:22EN
MBMatthew Berman· 2. Mai 2024Harrison Chase on Planning, Interface Design and Memory for AI AgentsMatthew Berman, Harrison Chase · Forward FutureThe LangChain CEO outlines open questions for agent builders, with commentary from Matthew Berman on oversight, workflows and memory.AI agentsAgent orchestrationAgent memory+2
27:32EN
No Priors: AI, Machine Learning, Tech, & Startups· 28. März 2024Podcast · 2 StimmenFrom a side project to 700 integrations: Harrison Chase on what still blocks agentsModeration: Sarah Guo, Elad GilThe LangChain CEO walks through a two-year churn of patterns, and why memory, planning, and few-shot data still matter more than swapping models.AgentenAgent EngineeringAgent memory+3
37:18EN
No Priors: AI, Machine Learning, Tech, & Startups· 4. Mai 2023Podcast · 2 StimmenUse Retrieval for a Wi-Fi Password. Use Experts for a Company's Private Language.Moderation: Sarah Guo, Elad GilGoogle Brain's Kelvin Guu on REALM, FLAN, model surgery, and why personalizing large models is still an unsolved interface problem.RAG & WissenRetrieval-Augmented GenerationFine-Tuning+3
1:30:52EN
Lex FridmanPodcast · 2 StimmenBuilding Minds from Unified Theories: Nate Derbinsky on Cognitive Architectures, Soar, and the Case for ForgettingGast: MIT AGI · Moderation: Lex FridmanA guest lecture in MIT's AGI course on how cognitive architectures try to assemble human-level intelligence, and how studying human memory made the Soar architecture faster and better.AgentenAGIAI research+3
10:16EN
Lex FridmanPodcast · 2 StimmenReasoning Without Logic: Yann LeCun on Teaching Neural Networks to ThinkGast: Yann Lecun · Moderation: Lex FridmanYann LeCun explains why he believes neural networks can reason, and what memory, recurrence and continuous representations would need to look like.Modelle & TrainingML-GrundlagenDeep Learning+3