🗄️ Web Datasets - emschwartz · Scour

Show HN: WhiskeySour – A 10x faster drop-in replacement for BeautifulSoup 📖Readability Algorithms

news.ycombinator.com·7h·Hacker News

Show HN: GitHub Directory for Public APIs 💰Web Monetization API

github.com·12h·Hacker News

Vector Database 📊Vector Databases

newsletter.systemdesign.one

·12h

Show HN: Read and Echo – Turn any text into structured language practice 💡Readwise

news.ycombinator.com·3h·Hacker News

The Multilingual Emotion Wheel ✨Gemini

Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testing 🛡️AI Safety

allbrainsbelong.org 🎨ChromaDB

allbrainsbelong.org·2h

Fast Attention for Short Sequences 📏ANN Benchmarks

blog.qwertyforce.dev·6h·Hacker News

Rank & Select 🗂️Vector Indexes

curiouscoding.nl·5h

Free Interview Transcription with AI 🤖Web Crawling Politeness

noscribe.de·22h

Evian: Towards Explainable Visual Instruction-tuning Data Auditing 🔍AI Interpretability

Share of electricity production from coal (by year) 🏭Electricity Markets

ourworldindata.org·10h

deepseek-ai/DeepSeek-V4-Flash 🏗️LLM Infrastructure

huggingface.co·1d·Hacker News

Nexlev YouTube Research & Analytics 📊Feed Optimization

chromewebstore.google.com·14h

Civic-SLM is a domain-specialized fine-tune of Qwen2.5-7B for U.S. govt data 🔍Paradedb

itsmeduncan.com·19h·Hacker News

Show HN: How LLMs Work – Interactive visual guide based on Karpathy's lecture 🔤Tokenization

ynarwal.github.io·1d·Hacker News

Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond 📊Vector Databases

yao-open-skills/skills/yao-bayesian-skill at main · yaojingang/yao-open-skills 🦙Ollama

github.com·11h

Embeddings | Gemini API | Google AI for Developers ✨Gemini

ai.google.dev·2d

https://research.perplexity.ai/articles/advancing-search-augmented-language-models 🏆LLM Benchmarking

research.perplexity.ai·2d

Log in to enable infinite scrolling