Résultats
42 articlesTrier
17:56EN
AI Engineer· 25 oct. 2026How 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.
20:58ENAI Engineer· 25 oct. 2026Vinoo Ganesh on Making Financial AI Cite Every NumberVinoo Ganesh · KeplerKepler CEO Vinoo Ganesh explains why financial AI should retrieve and cite figures while deterministic software handles the math. His design makes traceability, retrieval quality, and tenant security part of the answer itself.
1:08:54EN
20VC with Harry Stebbings· 26 sept. 2026Podcast · 2 voixParag Agrawal on Web Search and Business Models for AI AgentsInvité : Parag Agrawal · Anime : Harry StebbingsParallel’s co-founder explains why agent search needs different economics, how content owners might be paid and why agent safety requires more than model capability.
55:19EN
Sequoia Capital· 25 août 2026PodcastHuman Click Data Is a Bug: Rebuilding Search for a Web of AgentsParag Agrawal, former Twitter CEO and founder of Parallel Web Systems, argues that agents will query the web a thousand times more than people, and that both search infrastructure and the ad-supported internet have to be rebuilt for that customer.
2:38:48EN
Cognitive Revolution "How AI Changes Everything"· 26 avr. 2026PodcastA thousand searches for five cents, and a high score that did not require cheatingAnime : Nathan LabenzOn a Cognitive Revolution morning show, Ceramic’s Anna Patterson collides cheap search with GPT-5.5’s clean Vending-Bench run, Zvi’s case for model welfare, and analog chips that cut matrix-multiply energy about thirtyfold.
31:26ENSequoia Capital· 14 avr. 2026PodcastChatGPT Opened 65 Pages to Buy a Shower HeadProfound CEO James Cadwallader argues that the internet's front door is the same, but an agent now walks through it, and marketing has to be rewritten for that visitor.
1:37EN
Matthew Berman· 18 févr. 2026Matthew Berman’s OpenClaw Knowledge BaseMatthew Berman · Forward FutureA personal agent captures links, follows related sources and makes saved material searchable in natural language.
1:52:38ENMatthew Berman· 22 nov. 2025Open Models, AI Infrastructure, and Search: Four PerspectivesMatthew Berman, Nick Wentz, Himanshu Tyagi, Misha Laskin, Bryan Catanzaro, Robby Stein · Forward FutureForward Future speaks with leaders from Sentient, Reflection AI, NVIDIA, and Google about openness, scaling, safety, and AI-powered search.
44:49EN
No Priors: AI, Machine Learning, Tech, & Startups· 5 sept. 2025Podcast · 2 voixHow OpenEvidence Became the Clinical OS for 40% of U.S. DoctorsAnime : 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.
45:17ENNo Priors: AI, Machine Learning, Tech, & Startups· 7 août 2025Podcast · 2 voixA Click From OpenAI Is 750 Times Harder Than From Google a Decade AgoAnime : 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.
0:54ENMatthew Berman· 6 juin 2025Matthew Berman Demonstrates ChatGPT Connectors and Deep ResearchMatthew Berman · Forward FutureIn a 2025 demonstration, connected services supply information for a natural-language question about recent HubSpot deals.
31:34ENNo Priors: AI, Machine Learning, Tech, & Startups· 15 mai 2025Podcast · 2 voixOne Company Now Holds as Many Documents as the Entire Early WebAnime : 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.
30:46ENNo Priors: AI, Machine Learning, Tech, & Startups· 24 avr. 2025Podcast · 2 voixDeep Research Turned Web Browsing into a Trainable ProblemAnime : 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.
0:51ENMatthew Berman· 21 mars 2025Claude Adds Web Search: A First LookMatthew Berman · Forward FutureMatthew Berman enables Claude’s web search and tries a query about his latest YouTube video in March 2025.
32:46ENSequoia Capital· 25 févr. 2025PodcastDon't draw the flowchart: OpenAI's Deep Research team on training agents end to endIsa Fulford and Josh Tobin explain why Deep Research was trained with reinforcement learning on hard browsing tasks instead of a human-written graph of model calls.
44:48ENSequoia Capital· 29 oct. 2024PodcastEnterprise Google Failed for Twenty Years. A Search Veteran Finally Made It Work.Glean CEO Arvind Jain on why company search is harder than the public web, why RAG lives or dies on retrieval, and what work looks like when every employee has an AI assistant.
24:26ENMatthew Berman· 20 août 2024SearchGPT vs. Perplexity vs. Google: A 2024 Hands-On ComparisonMatthew Berman · Forward FutureMatthew Berman compares answers, sources, freshness, local results and specialized search tools across three services.
3:02:16EN
Lex Fridman· 19 juin 2024Podcast · 2 voixThe journey begins after the answer: Perplexity CEO Aravind Srinivas on search and curiosityInvité : Aravind Srinivas · Anime : 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 juin 2024PodcastA Tenth of Google's Index, 99.9% Recall: How 20 People Built Brave SearchAnime : 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.
1:27:01ENCognitive Revolution "How AI Changes Everything"· 8 avr. 2024PodcastThree Million Emails, Ten LLM Calls, Six Models: Shortwave's RAG PlaybookAnime : 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 avr. 2024PodcastThe Right Size of an AI Task Is Whatever You Can CheckAnime : 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.
9:19ENMatthew Berman· 28 mars 2024Trying an Open-Source Answer Engine with Groq and OllamaMatthew Berman · Forward FutureMatthew Berman installs a Perplexity-inspired search app, demonstrates a hosted-model configuration and attempts an unfinished local-model integration.
1:06:54ENCognitive Revolution "How AI Changes Everything"· 5 mars 2024PodcastGoogle Gives You 33 Million Results. Exa Wants 54.Anime : 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.
1:32:19ENCognitive Revolution "How AI Changes Everything"· 29 févr. 2024PodcastHis 2018 Prompting Paper Was Rejected. His Search API Now Beats GoogleAnime : Nathan LabenzRichard Socher traces You.com from a rejected unified NLP model to an LLM-native web index, three assistant modes, and a very low P(doom).Charger plus24 sur 42 affichés