💻 Local LLMs

Model Quantization, Inference Optimization, GGUF Format, Privacy-preserving AI

Ollama's new app
simonwillison.net·10h
🐚Shell Monads
New algorithms enable efficient machine learning with symmetric data
news.mit.edu·1d·
Discuss: Hacker News
💎Information Crystallography
#2 FC – Video Editing with FCP, Claude APIs, Bluetooth Messaging, AI Crawl Wars
furrycircuits.io·1d·
Discuss: Hacker News
🚀Indie Hacking
Researchers test the trustworthiness of AI by teaching it to play sudoku
techxplore.com·2d·
Discuss: Hacker News
🔲Cellular Automata
Some good AI philosophy
jmason.ie·3d
🔲Cellular Automata
What is an AI-first software company?
varungodbole.com·17h·
Discuss: Hacker News
⚙️TLA+
Do We Have Data to Train New AI?
labs.adaline.ai·4h·
Discuss: Hacker News
🔲Cellular Automata
Novel Pivoted Cholesky Decompositions for Efficient Gaussian Process Inference
arxiv.org·2d
📐Linear Algebra
RoD-TAL: A Benchmark for Answering Questions in Romanian Driving License Exams
arxiv.org·2d
🤖Automated Parsing
A Gold Standard Dataset and Evaluation Framework for Depression Detection and Explanation in Social Media using LLMs
arxiv.org·2d
🔍Information Retrieval
Do Large Language Models Understand Morality Across Cultures?
arxiv.org·1d
📝Text Parsing
Data-Driven Greenhouse Climate Regulation in Lettuce Cultivation Using BiLSTM and GRU Predictive Control
arxiv.org·1d
⚡Incremental Computation
Studying Disinformation Narratives on Social Media with LLMs and Semantic Similarity
arxiv.org·2d
📰Content Curation
Past Meets Present: Creating Historical Analogy with Large Language Models
arxiv.org·7h
🕰️RetroCRDTs
Introducing LangExtract: A Gemini powered information extraction library
developers.googleblog.com·22h·
Discuss: Hacker News
🏰Medieval Parsing
Image Captioning via Compact Bidirectional Architecture
arxiv.org·1d
🤖Advanced OCR
A guide to optimizing performance and security for MCP servers
dev.to·1d·
Discuss: DEV
👁️Observatory Systems
Data-Driven and Participatory Approaches toward Neuro-Inclusive AI
arxiv.org·1d
🤖AI Curation
When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification
arxiv.org·2d
🧮Kolmogorov Complexity
Libra: Assessing and Improving Reward Model by Learning to Think
arxiv.org·1d
📊Learned Metrics