二〇二六年十月八日
收録 14 篇
- nanoMuse: An Open-Source Personal Agent for Every Device You Own
- Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness
- Long-WAM: Scaling the Context of World-Action Models
- STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
- Quoting Ben Affleck
- DeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0
- Claude Haiku 5.5
- Secret protection must scale with software
- GPT-6 and Intelligent UI for everyone
- Helping teens learn, plan, and shape the future of AI
- Multimodal open d1 decision models for the edge
- Anti-Patterns in Software Blogging
- Scaling Decision Optimization to 100 Million Variables and Beyond with mPDLP in NVIDIA cuOpt
- Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses