Technology & AI
Free AI agent tutorial crosses 82,000 GitHub stars
Datawhale's hello-agents repo teaches building AI agents from scratch with ReAct, GRPO and MCP protocols, all for free.
AI Agents
AI agents explained — autonomous assistants, coding agents and the research on where they work and where they fail.
117 stories
Technology & AI
AI content extraction scores 97.4 on enterprise documents
A new arXiv submission argues content extraction is the perception layer for enterprise AI agents, scoring 97.4 on a 180-document corpus.
Technology & AI
NVIDIA RTX Spark brings 1-petaflop AI to Windows laptops
NVIDIA's RTX Spark puts one petaflop of FP4 AI into Windows laptops using a Blackwell GPU and Grace CPU, with preorders open and October 16 shipping.
Technology & AI
OpenAI trains AI agents on Ironclad contracts
OpenAI is training AI agents on Ironclad's contracting platform to advance computer use for professional work, with no model or timeline given.
Technology & AI
AI agent for chip verification hits 95% accuracy
An arXiv preprint turns chip simulation dumps into a searchable database for verification engineers, hitting 95.33% on 150 queries.
Technology & AI
CourseChat AI tutor picks 8B model over bigger rivals
Lethbridge researchers built CourseChat, an on-premises RAG tutor for six business courses, where bigger AI models failed the classroom speed test.
Technology & AI
AI agent skill scanners evaded 97% by Huawei researchers
A preprint from Huawei Research Zurich shows that scanners for malicious AI agent skills fail against an attacker who knows the detector.
Technology & AI
CoreWeave ships NVIDIA Vera Rubin, Cognition reports 4.8x speedup
CoreWeave is among the first clouds to deliver NVIDIA's Vera Rubin NVL72, with Cognition reporting 4.8x higher token throughput on real engineering
Technology & AI
LLVM trends on GitHub as AI agents target compiler code
LLVM, the compiler infrastructure behind Clang and Rust, surfaced on GitHub's daily trending list with 40,784 total stars.
Technology & AI
GRPO step-level bias: GRAFT graph method claims gains on agent tasks
An arXiv preprint proposes GRAFT, a graph framework for step-level credit in agentic RL, reporting gains over GRPO on multi-turn benchmarks.
Technology & AI
Rivet Actors hits GitHub trending with 20ms cold-start claim
Rivet Actors, a Rust open-source project trending on GitHub, claims 20ms cold starts and 0.6KB per instance for stateful AI agent workloads.
Technology & AI
Pistis multimodal models blend distillation and RL training
The Pistis report describes 27B and 9B multimodal models built on Qwen that alternate distillation and reinforcement learning in one training loop.