Claude 网页、桌面和移动端将默认启用 auto mode
AIHOT ·
Claude 官方宣布，下周起 Pro、Max 和 Team 套餐在 Claude 网页、桌面和移动端应用中的会话将默认以 auto mode 运行。auto mode 不再逐步请求用户批准，而是由自动检查拦截高风险操作，用户可随时切回手动模式。其引用的 Claude Code 更新提到 auto mode 用独立分类器审查 shell 命令，测试中拦…
原文内容 · 暂无该语言译文AI News · 2026-10-22
按本站收录日期（UTC）归档，不代表事件发生于当天；原公告、聚合源发布与收录时间分别标注。
返回资讯列表Donating Agent Skills to the Agentic AI Foundation
Simon Willison ·
Donating Agent Skills to the Agentic AI Foundation News today from Anthropic: We’re committed to keeping Agent Skills open, community-driven, and vendor-neutral. Today, we are d…
原文内容 · 暂无该语言译文How to Read Data into GPU Memory in Python with NVIDIA GPUDirect Storage
NVIDIA Technical Blog ·
GPU applications are processing ever-growing datasets with increasingly powerful accelerators. According to the 2025 Stanford AI Index, compute for notable AI... GPU application…
原文内容 · 暂无该语言译文Learning-Enhanced Observer for Sensorless Task-Null-Space Compliant Control
arXiv cs.RO ·
This paper presents a novel framework integrating a robust wrench observer with a hybrid pose and force controller for physical Human-Robot Interaction (pHRI). In pHRI tasks, ro…
原文内容 · 暂无该语言译文pplx-embed-v2-late Technical Report
arXiv cs.CL ·
In this report, we introduce pplx-embed-v2-late, a pair of 0.6B and 9B multilingual and multimodal late-interaction models. Both models achieve state-of-the-art results within t…
原文内容 · 暂无该语言译文From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
arXiv cs.CL ·
Voice agents increasingly require reliable tool use from speech, whereas prominent tool-calling benchmarks remain text-based. We study whether verified text benchmarks can be co…
原文内容 · 暂无该语言译文$\mu_0$: A Scalable 3D Interaction-Trace World Model
arXiv cs.RO ·
World models that capture how actions induce physical change enable scalable robot learning without reliance on embodiment-specific action labels. Pixel-space video models provi…
原文内容 · 暂无该语言译文Anthropic 指南：何时把子智能体合并进主 Agent 循环
AIHOT ·
Anthropic Applied AI 团队发布指南，讲解何时把 orchestrator 下的路由器、规划器和领域子智能体合并进单个主 Agent 循环。文中对比显示，带 skills 的单智能体在质量上常优于一提示全包和子智能体设计，且成本和延迟更低，一家客户改用单循环后运行时间约快 2x。
原文内容 · 暂无该语言译文MiniMax Code 桌面端推出 Mini App 长运行应用功能
AIHOT ·
MiniMax 在 MiniMax Code 桌面应用（macOS / Windows）本地会话中推出 Mini App，一种带前端和后端的长运行应用，以插件形式安装并与 Agent 双向调用，让 Agent 的工作停留在常驻页面而非散落各对话中。
原文内容 · 暂无该语言译文Cloudflare links vulnerability discovery to defense with OpenAI
OpenAI ·
Cloudflare uses OpenAI Daybreak to investigate vulnerabilities and propose fixes for review. Its developers use Codex to build faster and improve code quality.
原文内容 · 暂无该语言译文