A language model built for the public good
jmason.ie·2d
💻Local LLMs
How the fight over what it means to be human has dramatically changed
vox.com·2h
🧲Magnetic Philosophy
BitChat will fail for the same reason FireChat, Reticulum and Bridgefy failed
seriousaboutech.com·22h·
Discuss: Hacker News
📼Cassette Networks
Tetris in a Single Line of Code
survex.com·2d·
Discuss: Hacker News
🕹️Retro Gaming
Open‑source tool for async team updates
asyncstatus.com·20h·
Discuss: Hacker News
🔄Sync Engine
Want AI agents to work together? The Linux Foundation has a plan
zdnet.com·3d·
Discuss: Hacker News
🏠Homelab Federation
From zero to RAG engineer: 1200 hours of lessons so you don't repeat my mistakes
bytevagabond.com·2d·
Discuss: Hacker News
📄Text Chunking
Software Engineering Has Always Been Context Engineering
agenticcoding.substack.com·2d·
Discuss: Substack
⚙️Proof Engineering
We Replaced ETL with MCP
rashidazarang.com·1d·
Discuss: Hacker News
🔌Interface Evolution
Curves, points, incidences and covering
arxiv.org·3d
📊Computational Geometry
Announcing Precomputed Reachability Analysis in Socket
socket.dev·2d·
Discuss: Hacker News
👁️System Observability
SoK: A Systematic Review of Context- and Behavior-Aware Adaptive Authentication in Mobile Environments
arxiv.org·3d
🎯Threat Hunting
How API-Driven Content Powers the Future of Streaming Platforms
dev.to·1d·
Discuss: DEV
🌊Streaming Systems
Deep Learning-based Prediction of Clinical Trial Enrollment with Uncertainty Estimates
arxiv.org·1d
🧠Machine Learning
Argumentatively Coherent Judgmental Forecasting
arxiv.org·1d
📊Feed Optimization
A Developer’s Guide to Go’s Garbage Collection: Mastering the Tri-Color Algorithm
dev.to·3d·
Discuss: DEV
🧠Memory Allocators
High-Performance Go: Mastering Memory Mapping and Direct I/O for Terabyte-Scale Data Processing
dev.to·2d·
Discuss: DEV
🌊Stream Processing
Weak-to-Strong Generalization with Failure Trajectories: A Tree-based Approach to Elicit Optimal Policy in Strong Models
arxiv.org·5d
🧮Kolmogorov Bounds
Security practices in AI development
arxiv.org·3d
🔒WASM Capabilities
Training language models to be warm and empathetic makes them less reliable and more sycophantic
arxiv.org·3d
🎙️Whisper