local LLMs, small LLMs, mixture of experts

R²D²: Perception-Guided Task & Motion Planning for Long-Horizon Manipulation
developer.nvidia.com·2d
🎛️interfaces
Flag this post
The Paradox of a Principled Machine
artificiallyintelligentspace.substack.com·7h·
Discuss: Substack
🤝Multi-Agent Systems
Flag this post
Why is AI Generated Rust slow when compared with Go/C#/Node/JavaScript
srid68.github.io·14h·
Discuss: Hacker News
🌊Stream Processing
Flag this post
DevTrends MCP – Real-Time Developer Intelligence for AI Coding Assistants
apify.com·12h·
Discuss: DEV, Hacker News
🌊Stream Processing
Flag this post
AI Slop vs. OSS Security
devansh.bearblog.dev·8h·
Discuss: Hacker News
☁️cloudflare
Flag this post
What's up with Anthropic predicting AGI by early 2027?
lesswrong.com·1d·
Discuss: Hacker News
🤝Multi-Agent Systems
Flag this post
ZkML Breakthrough: 13B Models Verified in 15 Minutes
lightcapai.medium.com·2d·
Discuss: Hacker News
🌊Stream Processing
Flag this post
Surrey Uni show AI systems based on the human brain's save energy
epsomandewelltimes.com·2d·
Discuss: Hacker News
🤝Multi-Agent Systems
Flag this post
Show HN: Multi-Agent Code Review
news.ycombinator.com·10h·
Discuss: Hacker News
🤖agents
Flag this post
My First Multi-GPU Kernel: Writing All-to-All for AMD MI300X
gau-nernst.github.io·2d·
Discuss: Hacker News
🌊Stream Processing
Flag this post
The Paradox of Intelligence
medium.com·26m·
Discuss: Hacker News
🤝Multi-Agent Systems
Flag this post
Can SAEs reveal and mitigate racial biases of LLMs in healthcare?
arxiv.org·1d
📍embeddings
Flag this post
OceanAI: A Conversational Platform for Accurate, Transparent, Near-Real-Time Oceanographic Insights
arxiv.org·1d
🤝Multi-Agent Systems
Flag this post
ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
arxiv.org·1d
🎛️interfaces
Flag this post
ScaleCall - Agentic Tool Calling at Scale for Fintech: Challenges, Methods, and Deployment Insights
arxiv.org·1d
🤖agents
Flag this post
Fortytwo's decentralized AI has the answer to life, the universe, and everything
theregister.com·2d·
Discuss: Hacker News
🤝Multi-Agent Systems
Flag this post
Single-agent Reinforcement Learning Model for Regional Adaptive Traffic Signal Control
arxiv.org·1d
🤝Multi-Agent Systems
Flag this post