World Labs CEO Dr. Fei-Fei Li: "The world is not made of words."
"Language models have given machines an extraordinary command of concepts, vocabulary, and reasoning, but the physical world, virtual or real, runs on a different substrate."
"Where language models learn the statistical structure of text, world models learn the statistical structure of space and time: how light falls on a surface, how a garden looks from an angle no camera has captured, how objects respond to force and follow the laws of physics."
"Language gave machines a way to talk about that world. World models are how machines will finally come to understand, imagine, reason and interact with it."
Full piece: https://t.co/C9qOJg5wuc
Not every AI feature needs a dedicated vector database.
If your data already lives in PostgreSQL, adding Pinecone, Qdrant, or Weaviate might be one moving part too many.
For many use cases, `pgvector` is enough.
It gives PostgreSQL native vector storage and similarity search.
That means you can keep your embeddings next to your relational data and still use the things PostgreSQL is already great at:
- joins
- filters
- pagination
- transactions
- indexes
The basic flow is simple:
1. Generate an embedding for your content
2. Store it in a `vector` column
3. Generate an embedding for the search query
4. Order results by cosine distance with `<=>`
5. Return the closest matches
Now your users can search by meaning, not just exact keywords.
A query like “how to secure an API” can return articles about authentication, JWT validation, and authorization, even if those exact words don’t appear.
In this article, I show how to build simple vector search in .NET using PostgreSQL, pgvector, Aspire, Ollama, MEAI, and Dapper.
Read the full article here: https://t.co/XiTjXOz2C4