Model Quantization, ONNX Runtime, Embedded Inference, TinyML

The Linus Method: How we simiplifed RFC reviews
devashish.me·2d·
Discuss: Hacker News
☁️Serverless Rust
The Coming Collapse of White-Collar Work
buildingbetter.tech·5h·
Discuss: Hacker News
🎚️Voice AI Systems
AI Keeps Shifting Right: Coping with the Limitations of Large Language Models
blog.sturdystatistics.com·4d·
Discuss: Hacker News
🏗️AI Infrastructure
They Don't Have the Money: OpenAI Edition
platformonomics.com·1d·
Discuss: Hacker News
🖥computers
A tangled web of deals stokes AI bubble fears in Silicon Valley - BBC
news.google.com·1d·
Discuss: DEV
🖥computers
Neon: Negative Extrapolation From Self-Training Improves Image Generation
arxiv.org·5d
🏗️AI Infrastructure
Tech With Tim: Why 1M People Tried This AI Coding Tool (Full Vibe Coding Tutorial)
dev.to·21h·
Discuss: DEV
vibe-coding
**Debunking the Common Sense Myth in AI: From Limited Experi
dev.to·2d·
Discuss: DEV
🏗️AI Infrastructure
Decoding Activation Functions: A Nine-Dimensional Signature for Network Harmony
dev.to·11h·
Discuss: DEV
🧠Neuromorphic Hardware
A Hybrid Subsystem Architecture To Elevate Edge AI
semiengineering.com·3d
Hardware Acceleration
H1B-KV: Hybrid One-Bit Caches for Memory-Efficient Large Language Model Inference
arxiv.org·4d
💻Local LLMs
ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL
arxiv.org·3d
🏗️AI Infrastructure
StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering
arxiv.org·3d
🏗️AI Infrastructure
Embrace the Limits: How AI's Constraints Fuel Innovation by Arvind Sundararajan
dev.to·3d·
Discuss: DEV
🎚️Voice AI Systems
IASC: Interactive Agentic System for ConLangs
arxiv.org·2d
💬Language Servers
MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
arxiv.org·2d
💻Local LLMs
Tech With Tim: Cancel Your AI subscriptions | This All-in-one AI is All You Need (ChatLLM Review)
dev.to·1d·
Discuss: DEV
🧠AI
I Tried 500+ New AI Tools, and Honestly, These Will Blow Your Mind
dev.to·3d·
Discuss: DEV
🤖AI agents
Nearly Instance-Optimal Parameter Recovery from Many Trajectories via Hellinger Localization
arxiv.org·3d
💻Local LLMs
(FULLY OPEN SOURCE) open-computer-use: Computer agents working on their own VMs
github.com·14h·
Discuss: Hacker News
☁️Serverless Rust