The Best Mattress Toppers for Every Type of Sleeper
(feeds.content.dowjones.io)
1.
2.
3.
Querying 3B Vectors
(news.ycombinator.com)
4.
How to Choose the Bamboo Sheets for You (2026)
(wired.com)
5.
Connes Embedding Problem
(news.ycombinator.com)
6.
7.
ChromaDB Explorer
(news.ycombinator.com)
8.
30% Off Tempur-Pedic Promo Codes | December 2025
(wired.com)
9.
Using Vectorize to build an unreasonably good search engine in 160 lines of code
(news.ycombinator.com)
10.
Prompt caching for cheaper LLM tokens
(news.ycombinator.com)
11.
Prompt caching: 10x cheaper LLM tokens, but how?
(news.ycombinator.com)
12.
Contextualization Machines
(news.ycombinator.com)
13.
28M Hacker News comments as vector embedding search dataset
(news.ycombinator.com)
14.
Naturepedic Promo Codes and Deals: 20% Off
(wired.com)
15.
16.
17.
Why Google’s File Search could displace DIY RAG stacks in the enterprise
(venturebeat.com)
18.
Ilo – a Forth system running on UEFI
(news.ycombinator.com)
19.
Meta Superintelligence Labs' first paper is about RAG
(news.ycombinator.com)
20.
Meta Superintelligence's surprising first paper
(news.ycombinator.com)
21.
Language models pack billions of concepts into 12k dimensions
(news.ycombinator.com)
22.
Language Models Pack Billions of Concepts into 12k Dimensions
(news.ycombinator.com)
23.
Language Models Pack Billions of Concepts into 12,000 Dimensions
(news.ycombinator.com)
24.
How big are our embeddings now and why?
(news.ycombinator.com)
26.
We Hit 100% GPU Utilization–and Then Made It 3× Faster by Not Using It
(news.ycombinator.com)
27.
Show HN: Bolt – A super-fast, statically-typed scripting language written in C
(news.ycombinator.com)
28.
Gemini Embedding: Powering RAG and context engineering
(news.ycombinator.com)
29.
30.
All AI models might be the same
(news.ycombinator.com)