vector embeddings
3 statements across 2 episodes · 1 bullish · 2 bearish · 3 people on the record · first statement Mar 28, 2025 by Dharmesh Shah · across every show →
Everything said about vector embeddings, oldest first
Mar 28, 2025 positive
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…”
Jul 28, 2025 negative
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…”
Jul 28, 2025 bearish
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.”