Recently updated channels

Pick one to see only that channelBrowse all channels →
Matthew Bermantoday +281AI Engineertoday +6The Builderstoday +1a16ztoday +2Theo - t3․ggtoday20VC with Harry Stebbingsyesterday +394Jane Streetyesterday +119Y Combinatoryesterday +1硅谷1012 days agoPragerU3 days ago

Results

1 articles
Sort
TopicHybrid searchSpeakers2 people
31:28EN
No Priors: AI, Machine Learning, Tech, & Startups· Feb 22, 2024Podcast · 2 speakersBolt 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.RAG & knowledgeRetrieval-augmented generationVector search+3