🚀 LanceDB - emschwartz · Scour

list ▴ archive ▴ index

robotameri.ca·1d

🏛️Internet Archive

AI giants are racing to secure shrinking memory. It’s creating opportunities for startups

sifted.eu·2d

💾Prompt Caching

Paths of MySQL, vector search edition

notes.eatonphil.com·3d

Open source USearch library jumpstarts ScyllaDB vector search

thenewstack.io·6d

SAE Feature Matchmaking (Layer-to-Layer) by Mitali M

greaterwrong.com·1d

🔍AI Interpretability

producthunt.com·1d

Modalities, a PyTorch-native Framework For Large-scale LLM Training and Research

arxiv.org·1d

🏗️LLM Infrastructure

AlgoVeri: An Aligned Benchmark for Verified Code Generation on Classical Algorithms

arxiv.org·16h

⚡Comptime Programming

Flickypedia Project Page

commons.wikimedia.org·1d

🏛️Internet Archive

monogram v1.1: fancy update + open source tools

datagoblin.itch.io·1d

🎨Design Tokens

andywingo/wastrel: WebAssembly-to-C compiler

codeberg.org·1d

🕸️WebAssembly System Interface

Gemini thinking | Gemini API | Google AI for Developers

ai.google.dev·2d

Kevin Scott: Building a Sandbox for Claude Code

thekevinscott.com·1d

🔌Claude Plugins

Quick Comparison of JVM Languages

jvmhost.com·1d·

Discuss: Hacker News

⚙️Language Runtimes

Compare up to 5 LLMs side-by-side, then fuse the best answers

llmcode.ai·1d·

Discuss: Hacker News

🏆LLM Benchmarking

Adventures in Neural Rendering

interplayoflight.wordpress.com·23h·

Discuss: Hacker News

📦Batch Embeddings

Show HN: High-performance bidirectional list for React, React Native, and Vue

suhaotian.github.io·3d·

Discuss: Hacker News

Parse, Don't Validate (2019)

news.ycombinator.com·23h·

Discuss: Hacker News

💾Binary Formats

When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing

zenodo.org·1d·

Discuss: Hacker News

🕳LLM Vulnerabilities

I used to be fervent embedded DSL fan many years ago (particularly in college wi...

news.ycombinator.com·1d·

Discuss: Hacker News

💾Binary Formats

Loading more...