Hacker News with Generative AI: Embeddings

Harnessing the Universal Geometry of Embeddings (arxiv.org)
We introduce the first method for translating text embeddings from one vector space to another without any paired data, encoders, or predefined sets of matches.
Machine Learning, Embeddings, Vector Spaces
123 points by jxmorris12 37 days ago | 40 comments
Embeddings are underrated (2024) (technicalwriting.dev)
Machine learning (ML) has the potential to advance the state of the art in technical writing. No, I’m not talking about text generation models like Claude, Gemini, LLaMa, GPT, etc. The ML technology that might end up having the biggest impact on technical writing is embeddings.
Machine Learning, Technical Writing, Embeddings
484 points by jxmorris12 46 days ago | 150 comments
Launch HN: Exa (YC S21) – The web as a database (ycombinator.com)
Hey HN! We’re Will and Jeff from Exa (https://exa.ai). We recently launched Exa Websets, an embeddings-powered search engine designed to return exactly what you’re asking for. You can get precise results for complex queries like “all startups working on open-source developer tools based in SF, founded 2021-2025”.
Search Engines, Embeddings, Startups, Open Source, Developer Tools
412 points by willbryk 52 days ago | 133 comments
Sharding Pgvector (pgdog.dev)
If you find yourself working with embeddings, you’ve shopped around for a vector database. pgvector is a great option if you’re using Postgres already. Once you reach a certain scale (about a million arrays), building indices starts taking a long time. Some workarounds, like parallel workers, help, but you still need to fit the whole graph in memory.
Databases, PostgreSQL, Embeddings, Vector Databases
86 points by levkk 93 days ago | 10 comments
How to Implement a Cosine Similarity Function in TypeScript (alexop.dev)
To understand how an AI can understand that the word “cat” is similar to “kitten,” you must realize cosine similarity. In short, with the help of embeddings, we can represent words as vectors in a high-dimensional space. If the word “cat” is represented as a vector [1, 0, 0], the word “kitten” would be represented as [1, 0, 1]. Now, we can use cosine similarity to measure the similarity between the two vectors.
Cosine Similarity, TypeScript, AI, Embeddings
86 points by alexop 111 days ago | 40 comments
The Structure of Neural Embeddings (seanpedersen.github.io)
A small collection of insights on the structure of embeddings (latent spaces) produced by deep neural networks.
Machine Learning, Deep Learning, Neural Networks, Embeddings
74 points by sean_pedersen 182 days ago | 4 comments
Embeddings are underrated (technicalwriting.dev)
Machine learning (ML) has the potential to advance the state of the art in technical writing. No, I’m not talking about text generation models like Claude, Gemini, LLaMa, GPT, etc. The ML technology that might end up having the biggest impact on technical writing is embeddings.
Machine Learning, Technical Writing, Embeddings
367 points by misonic 239 days ago | 176 comments
Go library for in-process vector search and embeddings with llama.cpp (github.com/kelindar)
This library was created to provide an easy and efficient solution for embedding and vector search, making it perfect for small to medium-scale projects that still need some serious semantic power.
Go, Vector Search, Embeddings, Open Source, Software
114 points by kelindar 243 days ago | 29 comments
Interpreting Clip with Sparse Linear Concept Embeddings (SpLiCE) (arxiv.org)
CLIP embeddings have demonstrated remarkable performance across a wide range of computer vision tasks. However, these high-dimensional, dense vector representations are not easily interpretable, restricting their usefulness in downstream applications that require transparency.
Computer Vision, Machine Learning, Embeddings, Interpretability, Artificial Intelligence
7 points by fzliu 267 days ago | 0 comments
Show HN: AIQ – A no-frills CLI for embeddings and text classification (github.com/taylorai)
aiq is a no-frills CLI for embeddings and text classification, inspired by the power of jq. It does 4 things:
Text Classification, Embeddings, Artificial Intelligence
91 points by andersonbcdefg 280 days ago | 6 comments
Knowledge graphs using Ollama and Embeddings to answer and visualizing queries (github.com/punnerud)
This application uses a local Llama model to answer queries, build embeddings, and create a knowledge graph for exploring related questions and answers.
Knowledge Graphs, Artificial Intelligence, Embeddings
122 points by punnerud 283 days ago | 9 comments
Fine-Tune Embeddings in Google Colab (research.google.com)
Fine-Tuning, Embeddings, Machine Learning, Google Colab
8 points by esleightholm 339 days ago | 1 comments
Quaternion Knowledge Graph Embeddings (2019) (arxiv.org)
Knowledge Graphs, Embeddings, Machine Learning, Artificial Intelligence
100 points by teleforce 429 days ago | 41 comments