Vector Embeddings
topic on 4 shows · 7 statements across 5 episodes
Latent Space 
My First Million 
A Product Market Fit Show 
the MAD Podcast
7 statements about Vector Embeddings, every show
Eskildsen: Vector embeddings are larger in data size than raw text
“Because they're in thousands of dimensions, the coordinate in the coordinate system is very counterintuitive, but the coordinate in the coordinate system is larger than the original data. If you take a paragraph of text, the coordinate that represents it is ac…”
Kevin Hou: Traditional vector embeddings have hit a performance ceiling
“It's evident through the years that we're actually hitting a ceiling on what is possible using these traditional vector embeddings. And over time, even the biggest models are approximating to around the same level of performance.”
Mohan: Vector embeddings fail at granular code retrieval queries
“For a lot of the systems, we do believe embeddings work, but for complex questions, We don't believe embeddings can encapsulate all the granularity of a particular query. Like imagine, imagine I have a question on a code base of find me all quadratic time algo…”
Shah: Graph representations may outperform standard vector chunking in RAG
“The reality is something gets lost in the chunking process in the, okay, well, those tend to, you know, like you don't really get the whole picture, so to speak, and maybe not even the right set of dimensions on the kind of broader picture. And it makes intuit…”
Van Luijt: Language is the most common use case for vector embeddings
“Language is the use case we see the most right now”
Van Luijt: Virtually every database now supports vector embeddings
“What we try to start to see now is that basically every database under the sun supports vector embeddings.”
Shah: Replacing keyword search with vector embeddings is a massive AI opportunity
“One of the biggest opportunities in AI right now is to do what Pandora did. Okay. Is there an industry where right now we're doing really stupid keyword based matching somehow it was very, very crude. If I can take that same dataset and convert it to vector em…”