

Up to 3.2x Faster Inference with LFM2.5-DSpark
(翻译)LFM2.5-DSpark 最高可将推理速度提升 3.2 倍
A Blog post by Liquid AI on Hugging Face

Start building with Nano Banana 2 Lite and Gemini Omni Flash
(翻译)使用 Nano Banana 2 Lite 与 Gemini Omni Flash 开始构建
Scale your ideas with Nano Banana 2 Lite, our fastest, most cost-efficient Gemini Image model, and Gemini Omni Flash for high-quality video and conversational editing.

How Generative Recommenders Are Redefining RecSys at Scale
(翻译)生成式推荐器如何重新定义大规模推荐系统
Recommender systems (RecSys) are one of the most ubiquitous machine learning problems in the consumer internet industry yet notoriously difficult to train and…

Agentic observability with Amazon OpenSearch Service MCP Apps
(翻译)使用 Amazon OpenSearch Service MCP Apps 实现智能体可观测性
Amazon OpenSearch Service now supports MCP Apps, which return interactive visualizations alongside your AI agent's text responses. Learn how a single, locally run MCP server lets your agent move from alert to trace to logs to root cause in one conversation, and how you can verify every step inline w
从 Memory 到 Skill:长周期 AI Agent 如何实现持续进化
历史记录能帮 Agent 想起过去,却不能保证它下一次真的会按正确方法做。MSCE 想补上的,正是“记得”和“会做”之间的这段空白。 01 Agent 能记住,不等于下次会做 Agent 已经不只是在对话框里给出一个答案,它们会进代码库找文件、打开浏览器查资料、调用工具继续往下做。但随着任务越拉越长,问题也跟着冒出来:隔几天...
103μs 降到 18μs 背后,Cursor 为何剑指英伟达,重写 GPU?
作者丨 郑佳美 编辑丨 岑 峰 &nbs

Anthropic 写给 AI Native 团队的完整开发手册
Anthropic 发布《The AI-Native SDLC Playbook》,揭示 AI 开发的核心瓶颈不在代码生成,而在流程协同。本文深入拆解 intent.md 到部署的产物链机制,探讨产品经理价值上升、审查前置等关键转变,为 AI 从业者提供一套可落地的项目系统改造思路。

特努斯接替库克任苹果CEO;OpenAI修复Codex多项额度Bug;中科院成都山地所解析吉隆泥石流成因
特努斯接替库克任苹果CEO;OpenAI修复Codex多项额度Bug;中科院成都山地所解析吉隆泥石流成因

Build observable enterprise agentic retrieval using Managed Amazon Bedrock Knowledge Base with AWS CloudFormation
(翻译)使用 Amazon Bedrock 托管知识库与 AWS CloudFormation 构建可观测的企业级智能体检索
This post builds an enterprise agentic retrieval solution on the Amazon Bedrock Managed Knowledge Base and Amazon Bedrock AgentCore. An agent reasons, routes across multiple knowledge bases, and returns cited answers, with seven layers of observability and both on-demand and continuous evaluation, a

字段层差异:颜色、文案、图标各自有独立的语义定义
在前序章节中, YAML 契约 已经证明了” 形式化为代码的规矩在机器世界里长什么样 “, 同一份规则文件(YAML)能被编译为四种机器格式:放在 AI 指令前面的规则(Prompt 前缀)、给代码自动校验用的规则(JSON Schema)、给设计师走查用的清单(Checklist)、给自动化流水线用的拦截规则(CI 规则)。机器拿到这些格式后,能在AI生成界面之前自动拦住违规内容。

超越偏移量延迟:PB 级规模下 Hudi 数据湖流水线的队列等待时间计算
在这篇文章中,作者探讨了用于分析、报表和机器学习的数据湖架构,并展示了在使用 Kafka 和 Apache Hudi 时如何管理消费者延迟指标。

SSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval
(翻译)SSAKG 2.0:用于结构联想序列记忆与基于上下文检索的开源软件包
arXiv:2609.01849v1 Announce Type: new Abstract: This article presents SSAKG 2.0, an open-source software package for constructing and operating Structural Sequential Associative Knowledge Graphs (SSAKGs). An SSAKG represents objects as graph vertices and ordered sequences as structural patterns of g
Training a coding model to paint watercolours with TRL and OpenEnv
(翻译)用 TRL 与 OpenEnv 训练代码模型绘制水彩画
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
