How a Nix flake made our polyglot stack (and new dev onboarding) fast and sane
🏗️Build Systems
Flag this post
LangChain Might Be the New WordPress of AI
🚀Performance
Flag this post
H-FA: A Hybrid Floating-Point and Logarithmic Approach to Hardware Accelerated FlashAttention
arxiv.org·1d
⚡Performance Optimization
Flag this post
Feature Stores 2.0: The Next Frontier of Scalable Data Engineering for AI
hackernoon.com·15h
🚀Performance
Flag this post
Fast Answering Pattern-Constrained Reachability Queries with Two-Dimensional Reachability Index
arxiv.org·1d
🌐Network Protocols
Flag this post
MedRECT: A Medical Reasoning Benchmark for Error Correction in Clinical Texts
arxiv.org·1d
🌐Network Protocols
Flag this post
I'm working on a project I've been dreaming about for months and it feels good
💻Programming
Flag this post
Contrastive Knowledge Transfer and Robust Optimization for Secure Alignment of Large Language Models
arxiv.org·2d
⚡Performance Optimization
Flag this post
AI Safety at the Frontier: Paper Highlights of October 2025
lesswrong.com·6h
🔍Reverse Engineering
Flag this post
Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph
arxiv.org·1d
🔀Parallel Computing
Flag this post
Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+
arxiv.org·2d
🚀Performance
Flag this post
Redundancy Maximization as a Principle of Associative Memory Learning
arxiv.org·15h
⚡Performance Optimization
Flag this post
Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization
arxiv.org·1d
🔀Parallel Computing
Flag this post
MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
arxiv.org·1d
⚡Performance Optimization
Flag this post
Balancing Cost, Power, and AI Performance
oreilly.com·1d
🚀Performance
Flag this post
Loading...Loading more...