Resultados
26 artículosOrdenar
1:35:29EN
Cognitive Revolution "How AI Changes Everything"· 1 sept 2026PódcastUber Burned a Year of Tokens in 13 Weeks. Retrieval Is How Agents WinPresenta: Nathan LabenzMongoDB Field CTO of AI Pete Johnson argues that agent performance now hinges on retrieval quality, not on stuffing million-token context windows.
44:52EN
Sequoia Capital· 24 jun 2026PódcastAn 80GB Wikipedia Cache Versus a 100GB Model That Holds the InternetEngram’s founders argue that stuffing a company into the context window is the expensive kind of memory—and that baking it into the weights can cut token use by two orders of magnitude.
44:49EN
No Priors: AI, Machine Learning, Tech, & Startups· 5 sept 2025Pódcast · 2 vocesHow OpenEvidence Became the Clinical OS for 40% of U.S. DoctorsPresenta: Sarah Guo, Elad GilFounder Daniel Nadler tells No Priors how a free search tool for physicians, not an answer engine for patients, took high-stakes clinical knowledge in 18 months.
31:34ENNo Priors: AI, Machine Learning, Tech, & Startups· 15 may 2025Pódcast · 2 vocesOne Company Now Holds as Many Documents as the Entire Early WebPresenta: Sarah Guo, Elad GilGlean CEO Arvind Jain tells No Priors why enterprise search was a graveyard, how transformers finally made it work, and why a product that searches too well can be too dangerous to sell.
1:29:02ENCognitive Revolution "How AI Changes Everything"· 15 feb 2025PódcastShe Never Sees a Row of Your Data. The Answers Still Clear 95%.Presenta: Nathan LabenzIllumex CEO Inna Tokarev Sela tells Nathan Labenz how a Platonic industry ontology, trained only on metadata, collapses enterprise software into one conversation.
44:26ENSequoia Capital· 13 feb 2025PódcastAn AI Application Is Still an ApplicationMongoDB's Sahir Azam tells Sequoia why vector search is a new primitive for unstructured data, not a replacement for transactions, and why retrieval quality is the last mile that gets AI into conservative enterprises.
1:21:53ENCognitive Revolution "How AI Changes Everything"· 19 jul 2024PódcastHippoRAG Matches Iterative Retrieval at One-Tenth the Online CostPresenta: Nathan LabenzA hippocampus-inspired knowledge graph lets multi-hop questions skip the brute-force document crawl.
3:02:16EN
Lex Fridman· 19 jun 2024Pódcast · 2 vocesThe journey begins after the answer: Perplexity CEO Aravind Srinivas on search and curiosityInvitado: Aravind Srinivas · Presenta: Lex FridmanIn 2022, Perplexity's first hire asked about health insurance — and four PhDs could not get a clear answer from Google.
1:25:10ENCognitive Revolution "How AI Changes Everything"· 15 jun 2024PódcastA Tenth of Google's Index, 99.9% Recall: How 20 People Built Brave SearchPresenta: Nathan LabenzJosep M. Pujol walks Cognitive Revolution through Brave's privacy-first index, hybrid retrieval stack, and the Search API Nathan Labenz now wants his own product team to use.
36:20ENNo Priors: AI, Machine Learning, Tech, & Startups· 6 jun 2024Pódcast · 2 vocesA Hundred Million Tokens in Context Would Cost $10 Million. Tengyu Ma Runs the RAG MathPresenta: Sarah Guo, Elad GilThe Stanford professor and Voyage AI founder argues that retrieval, not a giant context window, is how enterprises should manage private knowledge.
1:27:01ENCognitive Revolution "How AI Changes Everything"· 8 abr 2024PódcastThree Million Emails, Ten LLM Calls, Six Models: Shortwave's RAG PlaybookPresenta: Nathan LabenzFirebase founder Andrew Lee walks Nathan Labenz through the retrieval stack that turned a Gmail inbox into a working AI assistant.
1:23:09ENCognitive Revolution "How AI Changes Everything"· 3 abr 2024PódcastThe Right Size of an AI Task Is Whatever You Can CheckPresenta: Nathan LabenzElicit founders Andreas Stuhlmüller and Jungwon Byun walk through how a twelve-person research assistant cut summary hallucinations from 1.5 to 0.5, ships about every week and a half, and treats task decomposition as the way to spend more compute without a black box.
1:06:54ENCognitive Revolution "How AI Changes Everything"· 5 mar 2024PódcastGoogle Gives You 33 Million Results. Exa Wants 54.Presenta: Nathan LabenzWill Bryk, CEO of Exa, tells Nathan Labenz why search and research are different jobs, and why an AI librarian for the web has to be neural from the first filter.
31:28ENNo Priors: AI, Machine Learning, Tech, & Startups· 22 feb 2024Pódcast · 2 vocesBolt Memory onto GPT-4 and Cut Hallucinations by up to 50%Presenta: Sarah Guo, Elad GilPinecone CEO Edo Liberty tells Sarah Guo and Elad Gil how RAG, serverless vectors, and keeping knowledge outside the model make LLMs more reliable.
42:07ENNo Priors: AI, Machine Learning, Tech, & Startups· 15 feb 2024Pódcast · 2 vocesNotion’s Ivan Zhao: RAG Will Make Organizing OptionalPresenta: Sarah Guo, Elad GilThe Notion CEO tells No Priors why he bet the company on GPT-4, why embeddings matter as much as agents, and why software is entering a bundling cycle.
1:53:08ENCognitive Revolution "How AI Changes Everything"· 18 ene 2024PódcastWhen GPT-4 Writes SQL, Four Tables Is the Breaking PointPresenta: Nathan LabenzJuan Sequeda on why a knowledge graph is the accurate, explainable brain that foundation models do not have.
1:32:40ENCognitive Revolution "How AI Changes Everything"· 31 oct 2023PódcastThe Historian Who Taught GPT-3.5 to Beat GPT-4Presenta: Nathan LabenzMark Humphries on a kilometer of unread paper, fur-trade jargon that embeddings cannot see, and why cheap processing will force history to be rewritten.
1:26:30ENCognitive Revolution "How AI Changes Everything"· 24 oct 2023PódcastMost of this data has never been in a database: Chroma's wartime CTO on RAGPresenta: Nathan LabenzAnton Troynikov returns to The Cognitive Revolution to argue that retrieval quality is mostly the embedding, that Chroma should own the RAG loop, and that GPT still fails a basic Game of Life test of reasoning.
37:18ENNo Priors: AI, Machine Learning, Tech, & Startups· 4 may 2023Pódcast · 2 vocesUse Retrieval for a Wi-Fi Password. Use Experts for a Company's Private Language.Presenta: Sarah Guo, Elad GilGoogle Brain's Kelvin Guu on REALM, FLAN, model surgery, and why personalizing large models is still an unsolved interface problem.
1:56:16ENCognitive Revolution "How AI Changes Everything"· 6 abr 2023PódcastThey Used Humans as Stand-In AIs. Now 250,000 People Run Elicit.Presenta: Nathan LabenzOught's founders tell Nathan Labenz why open-ended reasoning has to be decomposed, supervised, and grounded—not scaled until it merely looks persuasive.
35:36ENNo Priors: AI, Machine Learning, Tech, & Startups· 16 mar 2023Pódcast · 2 vocesFeatured snippets stalled at 7%. A Google veteran used language models to hit 70%Presenta: Sarah Guo, Elad GilNeeva founder Sridhar Ramaswamy tells No Priors why answers always beat links, why privacy never sold the switch, and why most queries do not need the biggest model.
1:26:20ENCognitive Revolution "How AI Changes Everything"· 2 mar 2023PódcastForty Dollars to Index Joe Rogan: Chroma, Shovels, and the Wright Flyer Era of MLPresenta: Nathan LabenzChroma co-founder Anton Troynikov on embeddings as the storage layer for language-model apps, Stable Attribution, and why machine learning is still flying on intuition.
2:52:56ENLex Fridman· 15 sept 2021Pódcast · 2 vocesDouglas Lenat's 37-Year Bet That Common Sense Can Be Written DownInvitado: Douglas Lenat · Presenta: Lex FridmanSince 1984, Cyc has been encoding the unstated rules of the world so machines can reason instead of merely pattern-match.
20:34ENLex Fridman· 26 oct 2019Pódcast · 2 vocesTeaching Machines the Frameworks Humans Take for GrantedInvitado: David Ferrucci · Presenta: Lex FridmanDavid Ferrucci explains why AI needs shared interpretive frameworks, not just data and pattern matching, to reason and communicate like humans.Cargar másMostrando 24 de 26