최근 업데이트된 채널

선택하면 해당 채널만 표시모든 채널 보기 →

필터 결과

13개
정렬
1:35:29EN
Cognitive Revolution "How AI Changes Everything"· 2026년 9월 1일팟캐스트Uber Burned a Year of Tokens in 13 Weeks. Retrieval Is How Agents Win진행자 Nathan LabenzMongoDB Field CTO of AI Pete Johnson argues that agent performance now hinges on retrieval quality, not on stuffing million-token context windows.RAG와 지식검색 증강 생성(RAG)Agent memory+3
1:29:02EN
Cognitive Revolution "How AI Changes Everything"· 2025년 2월 15일팟캐스트She Never Sees a Row of Your Data. The Answers Still Clear 95%.진행자 Nathan LabenzIllumex CEO Inna Tokarev Sela tells Nathan Labenz how a Platonic industry ontology, trained only on metadata, collapses enterprise software into one conversation.RAG와 지식컨텍스트 엔지니어링Knowledge graphs+3
1:21:53EN
Cognitive Revolution "How AI Changes Everything"· 2024년 7월 19일팟캐스트HippoRAG Matches Iterative Retrieval at One-Tenth the Online Cost진행자 Nathan LabenzA hippocampus-inspired knowledge graph lets multi-hop questions skip the brute-force document crawl.RAG와 지식검색 증강 생성(RAG)Knowledge graphs+3
1:25:10EN
Cognitive Revolution "How AI Changes Everything"· 2024년 6월 15일팟캐스트A Tenth of Google's Index, 99.9% Recall: How 20 People Built Brave Search진행자 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.RAG와 지식Search & retrievalHybrid search+3
1:27:01EN
Cognitive Revolution "How AI Changes Everything"· 2024년 4월 8일팟캐스트Three Million Emails, Ten LLM Calls, Six Models: Shortwave's RAG Playbook진행자 Nathan LabenzFirebase founder Andrew Lee walks Nathan Labenz through the retrieval stack that turned a Gmail inbox into a working AI assistant.RAG와 지식검색 증강 생성(RAG)Vector search+3
1:23:09EN
Cognitive Revolution "How AI Changes Everything"· 2024년 4월 3일팟캐스트The Right Size of an AI Task Is Whatever You Can Check진행자 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.RAG와 지식검색 증강 생성(RAG)Search & retrieval+3
1:06:54EN
Cognitive Revolution "How AI Changes Everything"· 2024년 3월 5일팟캐스트Google Gives You 33 Million Results. Exa Wants 54.진행자 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.RAG와 지식Search & retrieval검색 증강 생성(RAG)+3
1:53:08EN
Cognitive Revolution "How AI Changes Everything"· 2024년 1월 18일팟캐스트When GPT-4 Writes SQL, Four Tables Is the Breaking Point진행자 Nathan LabenzJuan Sequeda on why a knowledge graph is the accurate, explainable brain that foundation models do not have.RAG와 지식Knowledge graphs검색 증강 생성(RAG)+3
1:32:40EN
Cognitive Revolution "How AI Changes Everything"· 2023년 10월 31일팟캐스트The Historian Who Taught GPT-3.5 to Beat GPT-4진행자 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.RAG와 지식검색 증강 생성(RAG)파인튜닝+3
1:26:30EN
Cognitive Revolution "How AI Changes Everything"· 2023년 10월 24일팟캐스트Most of this data has never been in a database: Chroma's wartime CTO on RAG진행자 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.RAG와 지식검색 증강 생성(RAG)Embeddings+3
1:56:16EN
Cognitive Revolution "How AI Changes Everything"· 2023년 4월 6일팟캐스트They Used Humans as Stand-In AIs. Now 250,000 People Run Elicit.진행자 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.RAG와 지식에이전트 엔지니어링평가(Evals)+3
1:26:20EN
Cognitive Revolution "How AI Changes Everything"· 2023년 3월 2일팟캐스트Forty Dollars to Index Joe Rogan: Chroma, Shovels, and the Wright Flyer Era of ML진행자 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.RAG와 지식검색 증강 생성(RAG)Embeddings+3
1:06:22EN
Unsupervised Learning: With Jacob Effron팟캐스트Perplexity's Bet: Search Becomes Answers, and Answers Become a Business진행자 Jacob EffronThe Perplexity CEO explains how a consumer AI search product is built, sequenced, and defended against Google.RAG와 지식검색 증강 생성(RAG)Search & retrieval+3