필터 결과
15개정렬
17:56ENHow Bridgewater Keeps Its AI Analyst Inside Permission BoundariesNikhil Benesch, Aaron Linsky · turbopufferAaron Linsky and Nikhil Benesch explain why search over an enterprise vault must honor document permissions without sacrificing recall or speed. Their solution combines vector indexing with native filtering to search hundreds of millions of vectors in roughly 120 milliseconds.
44:49ENHow OpenEvidence Became the Clinical OS for 40% of U.S. Doctors진행자 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.
45:17ENA Click From OpenAI Is 750 Times Harder Than From Google a Decade Ago진행자 Sarah Guo, Elad GilCloudflare CEO Matthew Prince on Content Independence Day, why traffic is a broken proxy for value, and how to price the holes in the models.
31:34ENOne Company Now Holds as Many Documents as the Entire Early Web진행자 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.
30:46ENDeep Research Turned Web Browsing into a Trainable Problem진행자 Sarah Guo, Elad GilOpenAI researcher Isa Fulford explains why a side project on read-only synthesis became an agent, when reinforcement fine-tuning is worth it, and why models will hack the search engine you gave them.
3:02:16ENThe journey begins after the answer: Perplexity CEO Aravind Srinivas on search and curiosity게스트 Aravind Srinivas · 진행자 Lex FridmanIn 2022, Perplexity's first hire asked about health insurance — and four PhDs could not get a clear answer from Google.
38:48ENShopify Built a Copilot, Not an Autopilot, for Every Merchant진행자 Sarah Guo, Elad GilShopify VP of Core Product Glen Coates on collapsing duplicate engines, shipping AI that proposes but never commits, and teaching storefront search to understand a sweater.
46:36ENAfter a decade of code search, Sourcegraph’s CTO says the coding-AI fight is outside the model진행자 Sarah Guo, Elad GilBeyang Liu on Cody, why keyword search still does most of RAG, and why CS fundamentals get more valuable as AI compresses the middleware.
3:11:35ENSearch was always a hack: Marc Andreessen on AI, truth, and the next internet게스트 Marc Andreessen · 진행자 Lex FridmanLex Fridman sits down with the Mosaic co-creator and Andreessen Horowitz founder to ask whether Google Search, the browser, and open-source AI survive the decade.
39:10ENNever Cite More Than Five Links: Perplexity's Bet on Answer Engines진행자 Sarah Guo, Elad GilFounded in August 2022, Perplexity was barely seven months old when its CEO and CTO sat down with No Priors to explain how an answer engine takes on Google.
35:36ENFeatured snippets stalled at 7%. A Google veteran used language models to hit 70%진행자 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.
1:45:58ENNine of ten colleagues said far-field speech was impossible게스트 Rohit Prasad · 진행자 Lex FridmanRohit Prasad, Amazon’s vice president and head scientist for Alexa, talks with Lex Fridman about conversational AI, the Alexa Prize, trust, and why a 20-minute chat is still years away.
1:21:38ENSearch Isn't Dying, It's Expanding: Robby Stein on Google's AI Mode and Building Products Relentlessly게스트 Robby Stein · 진행자 Lenny RachitskyGoogle Search's VP of Product explains how AI Overviews, Lens and AI Mode fit together, and the product principles he carried from Instagram Stories to Google.
1:11:56ENHow to Get ChatGPT to Recommend Your Product: A Practical Guide to Answer Engine Optimization게스트 Ethan Smith · 진행자 Lenny RachitskyGraphite CEO Ethan Smith explains how AEO differs from SEO, which levers move the needle, and how to measure and test what works.
32:41ENHow IBM Watson Won Jeopardy: A Moonshot Built on Engineering, Not a Breakthrough게스트 David Ferrucci · 진행자 Lex FridmanDavid Ferrucci tells Lex Fridman how he talked IBM into the Jeopardy challenge and how his team built Watson's search, scoring and confidence machinery in about four years.









