🏠 Self-hosted AI

Model Optimization, Inference Engines, LLM Quantization, Privacy-focused Deployments

MIT’s Survey On Accelerators and Processors for Inference, With Peak Performance And Power Comparisons
semiengineering.com·6h
🏗️AI Infrastructure
Flag this post
Raising the Bar on ML Model Deployment Safety
uber.com·1d
📱Edge AI
Flag this post
Torchforge – a PyTorch native library for scalable RL post-training
pytorch.org·1d·
Discuss: Hacker News
🏗️AI Infrastructure
Flag this post
Why self-hosting matters now more than ever in the age of cloud
xda-developers.com·9h
👨‍💻Self-Hosting
Flag this post
Freephdlabor: Customizable multiagent research automation system
freephdlabor.github.io·1d·
Discuss: Hacker News
🤖AI agents
Flag this post
One Memory Layer, Multiple Models (Claude, GPT, Llama, etc.)
github.com·19h·
Discuss: Hacker News
🏗️AI Infrastructure
Flag this post
Secure us with this AI ERA
dev.to·15h·
Discuss: DEV
🏗️AI Infrastructure
Flag this post
Context engineering
chrisloy.dev·1d·
Discuss: Hacker News
🎤Voice Interfaces
Flag this post
MLPrE -- A tool for preprocessing and exploratory data analysis prior to machine learning model construction
arxiv.org·1d
🏗️AI Infrastructure
Flag this post
PORTool: Tool-Use LLM Training with Rewarded Tree
arxiv.org·19h
💻Local LLMs
Flag this post
Retrieval Augmented Generation-Enhanced Distributed LLM Agents for Generalizable Traffic Signal Control with Emergency Vehicles
arxiv.org·19h
🤖AI agents
Flag this post
What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data
arxiv.org·19h
🎙️Whisper
Flag this post
“Systems thinking helps me put the big picture front and center”
towardsdatascience.com·1d
🤖AI agents
Flag this post
Never Forget a Thing: Building AI Agents with Hybrid Memory Using Strands Agents
dev.to·12h·
Discuss: DEV
🏗️AI Infrastructure
Flag this post
Scaling is the New “Just Add More RAM” — Why AI Needs a New Algorithm, Not a Bigger Wallet
dev.to·5h·
Discuss: DEV
🏗️AI Infrastructure
Flag this post
Turbocharge Your AI: A Smarter Way to Explore Decision Trees
dev.to·22h·
Discuss: DEV
📱Edge AI
Flag this post
Implicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interaction
arxiv.org·1d
🎤Voice Interfaces
Flag this post
The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy
arxiv.org·19h
🤖Swarm Robotics
Flag this post
Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning
arxiv.org·19h
📱Edge AI
Flag this post
Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing
arxiv.org·19h
🏗️AI Infrastructure
Flag this post