Run local LLMs with Ruby llama.cpp bindings
docuseal.com·16h·
Discuss: Hacker News
💻Local LLMs
2025 Hackaday Supercon: More Wonderful Speakers
hackaday.com·13h
⚙️DIY Electronics
Show HN: Artisans AI – I build a powerful AI creation suite
artisans-ai.com·1h·
Discuss: Hacker News
🏛Digital humanities
Google Chrome RCE (No Sandbox) via CanonicalEquality:EqualValueType()
ssd-disclosure.com·2d·
Discuss: Hacker News
🛡️WASM Security
Catch unsafe Rails migrations in development
github.com·9h·
Discuss: Hacker News
🧬PostgreSQL Forensics
Llmswap: Avoid LLM vendor lock-in – 10 providers with top LMArena models
github.com·3d·
Discuss: Hacker News
🌀Brotli Internals
Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
arxiv.org·1d
💻Local LLMs
Adaptive Bit-Error Rate Mitigation in QSFP28 Transceivers via Dynamic Digital Equalization
dev.to·1d·
Discuss: DEV
⚛️Quantum Codecs
PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
arxiv.org·2d
Effect Handlers
Moral Anchor System: A Predictive Framework for AI Value Alignment and Drift Prevention
arxiv.org·1d
🔲Cellular Automata
ArchitectHead: Continuous Level of Detail Control for 3D Gaussian Head Avatars
arxiv.org·2h
📐Projective Geometry
I reviewed the GMKtec NucBox M6 Ultra - and this mini PC has serious potential for the price
techradar.com·1d
🔌Operating system internals
VMRay SentinelOne Integration Delivers Full Threat Context
vmray.com·11h
👁️Observatory Systems
Iteration is all you need: ARC-2 solver inspired by Grover's search algorithm
github.com·3d·
Discuss: Hacker News
Incremental Computation