embeddings
Vector representations of words (or tokens) in a high-dimensional space, the form in which language models process text.
As defined in 336 | Anil Ananthaswamy on the Mathematics of Neural Nets and AI
Other definitions
Numerical vector representations of text, words, or concepts learned by neural networks that capture semantic relationships; used in machine learning to convert text into a format that models can process
How ChatGPT changed everything: Thoughts from the frontline of the AI/ML revolution
Where it comes up · 6
- When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer3 claims
- Ollama Changes Everything - Why Is Everyone Talking About It?1 claim
- Databricks: From Data to Decisions1 claim
- 336 | Anil Ananthaswamy on the Mathematics of Neural Nets and AI1 claim
- Andrej Karpathy Just 10x’d Everyone’s Claude Code1 claim
- How ChatGPT changed everything: Thoughts from the frontline of the AI/ML revolution1 claim
Most important claims · 8 of 8Search all claims for “embeddings” →
- In a transformer, input words are turned into high-dimensional vectors (embeddings) that flow through the network; the attention mechanism repeatedly massages these vectors layer by layer so each word's vector incorporates contextual information from the others, so that by the final layer the last vector carries enough context to predict the next word correctly (e.g., 'homework' after 'the dog ate my').336 | Anil Ananthaswamy on the Mathematics of Neural Nets and AI
- The setup for the Karpathy LLM wiki requires only 5 minutes and does not need a fancy vector database, embeddings, or complex infrastructure—it is literally just a folder with markdown files.Andrej Karpathy Just 10x’d Everyone’s Claude Code
- Intercom's Resolution Boss product uses medium-scale language models (not GPT-scale models) with embeddings and is designed with a conscious constraint: it never outputs anything not explicitly curated by customers, preventing hallucinations but limiting capability—a conservative, production-safe approach to generative AI in customer supportHow ChatGPT changed everything: Thoughts from the frontline of the AI/ML revolution
- Building effective agentic applications requires techniques beyond the model itself, including retrieval-augmented generation with vector databases and embeddings, and model evaluation to measure whether non-deterministic LLM behavior matches expectations, which is where Databricks has a strong right to win.Databricks: From Data to Decisions
- Ollama provides a REST API that enables custom applications to communicate with locally-running models, supports embeddings for building private document search capabilities, enables tool calling for complex automated tasks, and provides compatibility layers to redirect cloud-service-specific tools to run locally instead.Ollama Changes Everything - Why Is Everyone Talking About It?
- Writer's next approach used vector embeddings with chunking and stored results in a database for similarity search, then passed results to the LLM, but this caused two major problems: inaccurate answers from chunking artifacts and failure on concentrated data.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer
- Writer initially started with basic keyword search (regular search/querying of knowledge bases) before moving to vector embeddings.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer
- Vector embeddings with chunking and nearest-neighbor search was Writer's second major retrieval approach before moving to graph-based systems.When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge - Sam Julien, Writer