Results
26 articlesSort
1:35:29ENUber Burned a Year of Tokens in 13 Weeks. Retrieval Is How Agents WinHost Nathan LabenzMongoDB Field CTO of AI Pete Johnson argues that agent performance now hinges on retrieval quality, not on stuffing million-token context windows.
44:52ENAn 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.
44:49ENHow OpenEvidence Became the Clinical OS for 40% of U.S. DoctorsHost 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.
31:34ENOne Company Now Holds as Many Documents as the Entire Early WebHost 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.
1:29:02ENShe Never Sees a Row of Your Data. The Answers Still Clear 95%.Host Nathan LabenzIllumex CEO Inna Tokarev Sela tells Nathan Labenz how a Platonic industry ontology, trained only on metadata, collapses enterprise software into one conversation.
44:26ENAn 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.
1:21:53ENHippoRAG Matches Iterative Retrieval at One-Tenth the Online CostHost Nathan LabenzA hippocampus-inspired knowledge graph lets multi-hop questions skip the brute-force document crawl.
3:02:16ENThe journey begins after the answer: Perplexity CEO Aravind Srinivas on search and curiosityGuest Aravind Srinivas · Host Lex FridmanIn 2022, Perplexity's first hire asked about health insurance — and four PhDs could not get a clear answer from Google.
1:25:10ENA Tenth of Google's Index, 99.9% Recall: How 20 People Built Brave SearchHost 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.
36:20ENA Hundred Million Tokens in Context Would Cost $10 Million. Tengyu Ma Runs the RAG MathHost 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.
1:27:01ENThree Million Emails, Ten LLM Calls, Six Models: Shortwave's RAG PlaybookHost Nathan LabenzFirebase founder Andrew Lee walks Nathan Labenz through the retrieval stack that turned a Gmail inbox into a working AI assistant.
1:23:09ENThe Right Size of an AI Task Is Whatever You Can CheckHost 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.
Google Gives You 33 Million Results. Exa Wants 54.Host 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.
31:28ENBolt Memory onto GPT-4 and Cut Hallucinations by up to 50%Host 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.
42:07ENNotion’s Ivan Zhao: RAG Will Make Organizing OptionalHost 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.
1:53:08ENWhen GPT-4 Writes SQL, Four Tables Is the Breaking PointHost Nathan LabenzJuan Sequeda on why a knowledge graph is the accurate, explainable brain that foundation models do not have.
1:32:40ENThe Historian Who Taught GPT-3.5 to Beat GPT-4Host 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.
1:26:30ENMost of this data has never been in a database: Chroma's wartime CTO on RAGHost 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.
37:18ENUse Retrieval for a Wi-Fi Password. Use Experts for a Company's Private Language.Host Sarah Guo, Elad GilGoogle Brain's Kelvin Guu on REALM, FLAN, model surgery, and why personalizing large models is still an unsolved interface problem.
1:56:16ENThey Used Humans as Stand-In AIs. Now 250,000 People Run Elicit.Host 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.
35:36ENFeatured snippets stalled at 7%. A Google veteran used language models to hit 70%Host 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.
1:26:20ENForty Dollars to Index Joe Rogan: Chroma, Shovels, and the Wright Flyer Era of MLHost 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.
2:52:56ENDouglas Lenat's 37-Year Bet That Common Sense Can Be Written DownGuest Douglas Lenat · Host Lex FridmanSince 1984, Cyc has been encoding the unstated rules of the world so machines can reason instead of merely pattern-match.
20:34ENTeaching Machines the Frameworks Humans Take for GrantedGuest David Ferrucci · Host Lex FridmanDavid Ferrucci explains why AI needs shared interpretive frameworks, not just data and pattern matching, to reason and communicate like humans.
Load moreShowing 24 of 26








