Embeddings
topic on 6 shows · 16 statements across 16 episodes
Masters of Scale 
Latent Space 
No Priors 
Sourcery 
the MAD Podcast 
TBPN
16 statements about Embeddings, every show
Trojanowski: Cheaper inference is replacing graphs and embeddings for agent ontologies
“As models are getting cheaper and cheaper, more and more of that actually can just be done using inference instead of using determined, like things like graphs or things like embeddings.”
Pereyra: Harvey Is Likely the Largest Embeddings Consumer for Some AI Labs
“I think for some of the labs, we are like the largest consumer of embeddings.”
Simon Last: Vector Embeddings Make Hierarchical Workspace Organization Irrelevant
“I would say, I mean, the interesting thing is that with embeddings, it almost doesn't matter as much anymore, The AI doesn't really care what the tree structure is, for example. The, all, all the AI cares about is that there's a snippet of text that has the co…”
McCloy: Optimizing for semantic embeddings does not improve AI search ranking
“But I think as a tool to understand how these AI platforms are consuming your content, embeddings aren't that relevant. You're better off focusing on, like, just, again, having a good structured set of content that makes sense, like, to a human with, like, cle…”
Jain: Vector Search Alone Cannot Solve Enterprise Search
“There's a lot of focus on embeddings and vector search over the last few years, but that's actually only one part of, ah, building a good search system. Because if you think about an enterprise, ah, imagine a company that has been around for a few decades. You…”
Huber: Fuzzy search is most useful when users don't know the dataset
“Fuzzy search is really useful when people like are not, you know, experts in their own data, right? Is that if you're Google Drive, you know how to search for stuff pretty well, right? But like your users don't know how to search for the stuff that you've said…”
Shah: Graph Representations Offer Observability That Vector Embeddings Lack
“They're much more discoverable. You can kind of see it. There's observability to it versus kind of embeddings, which you can't really do much with as a human. You know, once they're in there, you can't pull stuff back out”
Embeddings will not scale for cross-session memory in real-time AI systems
“I don't think that like embeddings are going to be able to scale to, I think they work well for some of this as like kind of the MVP version of the experience, but I think you're going to need a different experience and it's Probably something like really smar…”
Mohan: Embeddings fail at complex codebase retrieval tasks like identifying quadratic algorithms
“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 codebase of find me all quadratic time algor…”
Goyal: Embeddings and LLMs will replace relational indexes for querying data
“LLMs and, you know, specifically embeddings are going to be core to how people actually query data, not, you know, traditional algebraic relational indexes.”
Raskin: AI Embedding Spaces Share a Universal Geometric Shape Across Languages
“The core insight is that you could build a shape that represents English, a shape that represents German, and just rotate one shape on top of the other to do translation. And even though there are words in one that don't exist in the other, the point which is …”
Liu: Structured LLM outputs unlock traditional computer science reasoning algorithms
“Embeddings really is kind of like the lowest hanging fruit, and using something like Instructor can really help produce a data structure, and then you can just use your computer science to reason about this data structure.”
Liberty: Proper embedding retrieval rarely requires keywords alongside embeddings
“Our research actually shows that when you do this well, we, you very rarely need keywords alongside embeddings, but getting embeddings to perform perfectly is, is actually, it could be quite intricate.”
Gil: RAG and Embeddings Are Under-Appreciated Relative to Impact
“I feel like RAG and embeddings are very under-discussed, or under-appreciated in some sense, relative to the impact that they really seem to be having, or starting to have, and I think Notion Q&A is a great example of that.”
Zhang predicts much faster, diverse new embedding models within couple years
“So I think for the next couple years, yeah, we will see a whole bunch of new embeddings maybe of different sites, and much, much faster than today.”
Embedding search and analytics enable developers to improve model reliability
“By looking at embeddings doing embedding search, doing analytics over embedding space you could give developers you know, at the minimum of a divining rod, if not a compass, to be able to improve their models and get to the level of reliability they want to ha…”