Tag
Dreamscale Labs（YC F26）推出面向机器人的实时云推理平台，以超低延迟提供前沿物理 AI 模型（如 VLA、WAM）的按需云端推理，免去购置昂贵 GPU 的成本。
Felix Rieseberg explains how the new version of Anthropic's Cowork moves model inference and the VM fully into the cloud, with per-session sandboxes, to fix battery, performance, and persistence issues of the local-VM approach.
GLM 5.3 Flash, an AI model, is now available on the Modal platform via Auto Endpoints for easy access and deployment.
Hetzner offers free access to the Qwen 3.8 27B AI model via an OpenAI-compatible API, claiming it performs better than GPT-5.6 Luna in tests.
The article compares the routes of two AI model architecture camps, Mamba and RWKV: Mamba targets cloud-side enterprise AI platforms, while RWKV targets on-device and edge devices, each adapting to different hardware and inference scenarios.
This paper systematically studies hybrid multi-agent systems combining cloud-based LLMs and on-device SLMs, revealing task-dependent optimal architectures and challenging the assumption that more frontier compute always improves performance.