Scaling HNSWs
simonwillison.net·2d
💾Cache Design
Flag this post
The Quiet Power of SQL
blog.sturdystatistics.com·23h·
Discuss: Hacker News
🦆DuckDB
Flag this post
Bluffbench: Effective agents need to prioritize evidence over preconceptions
simonpcouch.github.io·1d·
Discuss: Hacker News
🦙Ollama
Flag this post
Why Businesses Should Invest in Smart Analytics for Data Insights
lumenn.ai·1d·
Discuss: DEV
ClickHouse
Flag this post
Duck Hunt: Moving Bauplan from DuckDB to DataFusion
bauplanlabs.com·3d·
Discuss: Hacker News
🦆DuckDB
Flag this post
Bring Your Own Blob Storage?
nuon.co·23h·
Discuss: Hacker News
📁File Systems
Flag this post
Asynchronous Wait-Free Runtime Verification and Enforcement of Linearizability
arxiv.org·14h
Formal Verification
Flag this post
Automated Gait Anomaly Detection via Spatiotemporal Graph Neural Networks and Dynamic Thresholding
dev.to·13h·
Discuss: DEV
🔬Deep Learning
Flag this post
PepTriX: A Framework for Explainable Peptide Analysis through Protein Language Models
arxiv.org·14h
🧬Computational Biology
Flag this post
Provably Safe Stein Variational Clarity-Aware Informative Planning
arxiv.org·14h
🎯Reinforcement Learning
Flag this post
DenoGrad: Deep Gradient Denoising Framework for Enhancing the Performance of Interpretable AI Models
arxiv.org·14h
📱Edge AI
Flag this post
Tech With Tim: Finally, an AI Database That Actually Makes Sense
dev.to·15h·
Discuss: DEV
💰TigerBeetle
Flag this post
Convomem Benchmark: Why Your First 150 Conversations Don't Need RAG
arxiv.org·14h
🔍RAG
Flag this post
7 Best Self-Hosted AI Tools for Building Business Apps
dev.to·11h·
Discuss: DEV
🦙Ollama
Flag this post
Building Agentic AI with Amazon Bedrock – Part 1: Your First AI Agent (Beginner Friendly)
dev.to·16h·
Discuss: DEV
🦙Ollama
Flag this post
Bicycles Are All Your AI Agents Need
dev.to·1d·
Discuss: DEV
💬Prompt Engineering
Flag this post
Taurus MM: A Cloud-Native Shared-Storage Multi-Master Database
muratbuffalo.blogspot.com·3d·
Discuss: Hacker News
Ring Buffers
Flag this post
Positional Bias in Long-Document Ranking: Impact, Assessment, and Mitigation
arxiv.org·1d
🎯Vector Search
Flag this post
Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting
arxiv.org·14h
🛡️AI Security
Flag this post