Login
28M Hacker News comments as vector embedding search dataset
(clickhouse.com) by walterbell | view | 171 comments
Show HN: We cut RAG latency ~2× by switching embedding model
(myclone.is) by vira28 | view | 4 comments
Embedding models for RAG have converged
(agentset.ai) by midamurat | view | 0 comments
The Idiot Sandwich – On Embedding Alt Text
(shkspr.mobi) by blenderob | view | 0 comments
mgrep: searching codebases with embeddings
(github.com) by mustaphah | view | 0 comments
Token embeddings violate the manifold hypothesis
(arxiv.org) by airstrike | view | 0 comments
Do embeddings spaces behave like metric spaces?
(testingbranch.com) by mpcsb | view | 1 comments
Connes Embedding Problem
(en.wikipedia.org) by jerlendds | view | 0 comments
ShowHN: I made an embedding model that guesses where a picture was taken
(geospot.sdan.io) by sdan | view | 1 comments
How Proper Names Behave in Text Embedding Space
(vectors.run) by etoud | view | 1 comments
Vec2text – reconstruct text sequences from embeddings
(github.com) by gregsadetsky | view | 0 comments
YouTube Embedding Broken in iOS Flutter/Hybrid Apps – Google Working on a Fix
(issuetracker.google.com) by AuriR | view | 1 comments
Embedding Symbolic Equivalence into Symbolic Regression via Equality Graph
(arxiv.org) by ahsillyme | view | 0 comments
Token Embeddings Violate the Manifold Hypothesis
(arxiv.org) by lukeplato | view | 1 comments
Show HN: PrivateLink – Stop TikTok and others from embedding your info in links
(private-link.com) by huppp | view | 0 comments
Show HN: SatoriDB – Query 1B vectors on a laptop (SQLite for embeddings, Rust)
(github.com) by poperk | view | 0 comments
How to Use Embeddings
(christopherren.substack.com) by mnky9800n | view | 0 comments
Stop Blaming Embeddings, Most RAG Failures Come from Bad Chunking
by wehadit | view | 3 comments
The Idiot Sandwich – On Embedding Alt Text
(shkspr.mobi) by ColinWright | view | 0 comments
Joint Embedding Predictive Architecture (JEPA) for AGI
(turingpost.com) by andsoitis | view | 0 comments
EBind: Multi-modal embedding model that supports image, video, audio, text
(github.com) by rahimnathwani | view | 1 comments
Built an Energy-Based Model without training – just GloVe and GPT embeddings
(github.com) by kinders | view | 0 comments
Show HN: PyNIFE. 400-900× speedup for embedding-based retrieval pipelines
(github.com) by stephantul | view | 0 comments
Embedding resources into executables built using GCC
(kevinboone.me) by chmaynard | view | 0 comments
We found embedding indexing bottleneck in the least expected place: JSON parsing
(nixiesearch.substack.com) by shutty | view | 0 comments
Show HN: I built an SEO tool that uses embeddings to analyze content relevance
(keywordgrid.com) by adamclarke | view | 1 comments
Zembed-1: The Best Text-Embedding Model
(zeroentropy.dev) by medbar | view | 0 comments
Cross-Lingual News Dedup at $100/Month – Embeddings, Pgvector, and UnionFind
(yingjiezhao.com) by ethan_zhao | view | 0 comments
Fine-Tuning Qwen3 Embeddings for product category classification
(blog.ivan.digital) by ipotapov | view | 0 comments
EFF to Court: Don't Make Embedding Illegal
(eff.org) by hn_acker | view | 0 comments
Why are Agents better at searching with grep than embeddings?
by CShorten | view | 0 comments
Understanding Rope: From Rotary Embeddings to Context Extension
(mli0603.notion.site) by sebg | view | 0 comments
MemVector: Local Vector API, Storage and Embedding Engine for PHP
(github.com) by bruceduk | view | 0 comments
DEF Con 33 – Exploiting Shadow Data from AI Models and Embeddings [video]
(youtube.com) by ogig | view | 0 comments
Show HN: I Built Context+ AST and Embeddings for Codebase Understanding
(contextplus.vercel.app) by forloopcodes | view | 0 comments
Pplx-Embed: Embedding Models for Web-Scale Retrieval
(research.perplexity.ai) by jxmorris12 | view | 0 comments
Learning from Structure: Discord's Entity-Relationship Embeddings
(discord.com) by throwaway314155 | view | 0 comments
Show HN: Sift – Score your feed locally with EmbeddingGemma
(github.com) by shreyask | view | 0 comments
Show HN: Irpapers – Visual embeddings vs. OCR trade-offs in scientific PDFs
(github.com) by pvpv | view | 0 comments
Embedding Wren in Hare
(drewdevault.com) by tosh | view | 0 comments
Grip – Retrieval engine, no embeddings, no vector DB
(pypi.org) by Nivens_McTwisp | view | 1 comments
Show HN: CLI tool to analyze your Vector Embeddings!
(github.com) by gauravvij137 | view | 1 comments
Show HN: Getting Warmer – Daily word game scored by GloVe embedding similarity
(gettingwarmer.io) by frostadvisory | view | 0 comments
Generating vector embeddings for semantic search locally
(theconsensus.dev) by ibobev | view | 0 comments
Harmonic embeddings beat random init and work frozen – no tokenizer needed
(github.com) by atech-77 | view | 0 comments
Using Vector Embeddings to Audit Content Architecture
(drive.google.com) by Aduttya | view | 1 comments
Search the public domain through image embeddings
(faenum.com) by jlauf | view | 0 comments
VL-JEPA: Joint Embedding Predictive Architecture for Vision-Language
(arxiv.org) by andsoitis | view | 0 comments
Show HN: Resilient RAP – A self-healing pipeline for telemetry using embeddings
(github.com) by tarekclarke | view | 0 comments
Agentic search vs. embedding-based search vs. truth layers
(markmhendrickson.com) by mhendric | view | 0 comments