28 min listen
Edo Liberty: Solving ChatGPT Hallucinations With Vector Embeddings
FromEye On A.I.
ratings:
Length:
35 minutes
Released:
Mar 30, 2023
Format:
Podcast episode
Description
Edo Liberty, who helped create SageMaker while at Amazon's AI labs, is building out long-term memory for large language models using vector embeddings at Pinecone.io. Edo says it solves the problem of hallucinations in large models like ChatGPT, which as we all know is their primary drawback. Edo's approach is simple: Convert authoritative and trusted information into vectors and load them into a vector database for large language models to refer to, allowing them to give accurate answers. We have a new sponsor this week: NetSuite by Oracle, a cloud-based enterprise resource planning software to help businesses of any size manage their financials, operations, and customer relationships in a single platform. They've just rolled out a terrific offer: you can defer payments for a full NetSuite implementation for six months. That's no payment and no interest for six months, and you can take advantage of this special financing offer today at netsuite.com/EYEONAI
Released:
Mar 30, 2023
Format:
Podcast episode
Titles in the series (100)
Episode 6 - Julian Togelius: In this episode of Eye on AI, I talk to Julian Togelius, perhaps the most prolific researcher at the intersection of video games and artificial intelligence. Julian works on AI for games and games for AI. Some of his most significant work is in... by Eye On A.I.