2026-07-22（内容获取于 07/22 05:02）

OpenAI says Hugging Face was breached by its own pre-release models

TechCrunch · 07/22 04:56

OpenAI has come forward to claim responsibility for the Hugging Face breach, saying it was the result of internal testing gone awry.

中文介绍 OpenAI承认对Hugging Face的数据泄露事件负责。该公司表示，泄露是由于其内部测试预发布模型时发生错误所致。

The State of Simulation for Physical AI: An Overview

Hugging Face Blog · 07/22 04:00

中文介绍 本文概述了物理AI领域的仿真技术现状。它探讨了当前在为物理AI系统创建和利用仿真环境方面的进展、挑战和未来发展方向，旨在为理解该技术提供全面视角。

Jack Dorsey is taking on Slack with Buzz, a group chat platform for teams and their AI agents

TechCrunch · 07/22 03:43

Buzz is a group chat platform for the workplace that puts humans and their AI agents in the same conversation.

中文介绍 Jack Dorsey推出了名为「Buzz」的团队群聊平台，旨在与Slack竞争。该平台允许人类用户与他们的AI代理在同一对话中进行协作，专注于提升工作场所的沟通效率和智能化水平。

AI and the rise of the universal entertainment app

TechCrunch · 07/22 03:39

Over the past decade, streaming platforms competed by dominating individual formats like music, video, podcasts, or audiobooks. Now, as AI makes it easier to create, organize, and recommend content, those distinctions are fading, pushing companies like Spotify, Netflix, YouTube, and TikTok to become

中文介绍 过去十年，流媒体平台通过主导单一内容形式竞争。如今，随着AI技术使内容创建、组织和推荐变得更容易，音乐、视频、播客等形式的界限正在模糊，推动了如Spotify、Netflix、YouTube等公司向“通用娱乐应用”发展。

Bucking EV slowdown, Sila raises $300M to expand battery materials factory

TechCrunch · 07/22 03:36

Sila's fresh $300 million round will help it make enough of its silicon-carbon anode material to power more than 100,000 EVs.

中文介绍 尽管电动汽车市场放缓，Sila公司仍成功完成3亿美元融资，用于扩建其电池材料工厂。这笔资金将帮助Sila生产足够的硅碳阳极材料，以满足超过10万辆电动汽车的电池需求。

🔬Causal Models Need Causal Data - Xaira’s X-Cell model for Drug Discovery (Bo Wang & Ci Chu, Chief Discovery Officer & Chief AI Scientist)

Latent Space · 07/22 03:34

Xaira Therapeutics is all in on data generation for model building! We talk with Bo Wang and Ci Chu about how and why.

中文介绍 Xaira Therapeutics正全面投入数据生成以构建模型，特别是其用于药物发现的X-Cell模型。公司首席发现官Bo Wang和首席AI科学家Ci Chu讨论了数据生成的重要性及方法，强调因果模型需要因果数据支撑。

Substack adds an AI detector to help spot blogs written by no one

The Verge · 07/22 03:22

Substack will now help users determine whether what they're reading may have been written by AI. A new tool coming to the platform can scan posts, notes, replies, and comments to provide an estimate of how much text could be AI-generated or written with AI assistance, according to a blog post publis

中文介绍 Substack将推出一项新的AI检测工具，旨在帮助用户识别平台上由AI生成或AI辅助创作的内容。该工具能够扫描帖子、笔记、回复和评论，估算出文本中AI生成部分的比例。

An AI system helped Pakistani judges clear massive backlogs at $38.50 return per dollar invested

The Decoder · 07/22 03:12

A field experiment with 1,559 Pakistani judges found that the AI assistant JudgeGPT boosted case resolution by 6.3 percent. The catch: only judges who got hands-on training saw gains. Without it, the effect mostly disappeared. The researchers estimate a return of up to $38.50 per dollar invested. Th

中文介绍 一项针对1,559名巴基斯坦法官的实地实验显示，AI助理“JudgeGPT”使案件解决率提高了6.3%。然而，只有接受过实践培训的法官才看到了成效，未培训者效果甚微。研究人员估计每投资1美元，回报高达38.50美元。

Nintendo customers have no legal right to tariff refunds, company tells judge

Ars Technica · 07/22 03:09

Nintendo says Switch buyers got what they paid for, urges court to dismiss lawsuit.

中文介绍 任天堂向法官表示，其顾客无权获得关税退款。该公司认为Switch买家已经获得了他们所支付的产品，并敦促法院驳回相关诉讼。

This Former Intel CEO Wants to Jumpstart Moore’s Law With Light

Wired AI · 07/22 03:05

Pat Gelsinger wants to pave the way to ever more powerful artificial intelligence using tiny beams of light.

中文介绍 英特尔前CEO Pat Gelsinger计划通过利用微小光束技术，为实现更强大的AI铺平道路，以此“重新启动”摩尔定律。他希望通过光芯片技术突破现有计算瓶颈。

Einride bets $38M on EV charging as it scales electric trucking

TechCrunch · 07/22 02:48

The acquisition — Einride's first as a publicly traded company — will expand its EV-charging ecosystem as it works to scale its electric trucking business.

中文介绍 Einride公司投资3800万美元用于电动汽车充电业务，这是其上市后的首次收购。此举旨在扩大其电动汽车充电生态系统，并推动其电动卡车运输业务的规模化发展。

Apple teams up with Klarna to launch a lease-to-own program for iPhones, iPads, and Macs

TechCrunch · 07/22 02:18

The new leasing program is a big change for the hardware company, and comes as it looks to raise prices on many of its products.

中文介绍 苹果公司与Klarna合作，推出一项针对iPhone、iPad和Mac的“先租后买”计划。这项新的租赁项目对这家硬件公司而言是一大改变，正值其考虑上调多款产品价格之际。

Let Tom Hiddleston be your guide to Pompeii's final day

Ars Technica · 07/22 02:17

NatGeo's Pompeii: Out of Time fuses historical fact and imagination to bring city's last 24 hours to life.

中文介绍 国家地理频道推出纪录片《庞贝：时空之外》，由Tom Hiddleston主持，探索庞贝古城覆灭前的最后24小时。该片融合历史事实与想象，旨在追踪可能的幸存者，生动再现这座城市的末日。

Peak Design’s modular Field Bracket has a finder tag built-in

The Verge · 07/22 02:12

I am a very clumsy man. So clumsy, that I have AirTags hanging off practically every camera I own. Have I left my camera in an Uber? Yes. Have I left it on an airplane? Also yes. For me, finder tags are essential for my cameras. The problem is, strapping a finder tag to a camera is always cumbersome

中文介绍 Peak Design推出新款模块化相机支架“Field Bracket”，其最大亮点是内置了查找标签。此设计旨在解决用户容易丢失相机，以及需要额外加装AirTag等跟踪设备的痛点。

Data centers expected to use 4x more electricity by 2035

TechCrunch · 07/22 02:06

New data centers built through 2033 could consume as much electricity as India uses today.

中文介绍 预计到2035年，数据中心的电力消耗将增长4倍。据估算，到2033年新建的数据中心所消耗的电量，可能将相当于目前整个印度国家的用电总量。

koala73/worldmonitor

TypeScript · ★ 64,965 · 🍴 10,139 · 📈 1,167 stars today

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface

中文介绍 `worldmonitor` 是一个实时全球情报仪表板，利用AI技术聚合新闻、监测地缘政治事件及关键基础设施动态。它提供统一的态势感知界面，旨在帮助分析师、研究人员或企业迅速掌握全球宏观环境变化，提升决策效率。适用于需要持续追踪国际局势和重大事件的专业人士。

bojieli/ai-agent-book

Python · ★ 14,221 · 🍴 1,327 · 📈 4,434 stars today

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

中文介绍 本项目是李博杰所著《深入理解 AI Agent：设计原理与工程实践》的开源主仓库。它提供了全书的完整正文、可编译的 PDF 版本，以及与各章节内容配套的代码示例。该项目旨在为读者提供一个全面的学习资源，深入探讨 AI Agent 的设计原理、架构模式及实际工程应用。开发者、研究人员或对 AI Agent 领域感兴趣的学习者，可以通过本书理论结合实践，掌握构建和部署智能 Agent 的核心知识与技能。

tirth8205/code-review-graph

Python · ★ 24,458 · 🍴 2,346 · 📈 1,921 stars today

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

中文介绍 Code Review Graph是一个本地优先的代码智能图谱工具，专为MCP（多组件项目）和CLI环境设计。它构建了一个持久化的代码库映射，旨在优化AI编码工具的上下文理解，确保AI在代码审查和处理大型仓库时仅读取关键信息。通过大幅减少AI上下文长度，提升了代码理解效率和审查质量。

ayghri/i-have-adhd

★ 6,654 · 🍴 269 · 📈 1,846 stars today

A skill for your coding agent to stop it from burying the answer. ADHD-friendly output.

中文介绍 `i-have-adhd` 项目为AI编程代理提供了一个实用“技能”，旨在解决代理输出冗长或关键信息被掩盖的问题。它优化了AI的回答结构，使其更简洁、直接，尤其适合对注意力缺陷多动障碍（ADHD）友好的输出，确保用户能迅速捕获核心内容。主要服务于追求高效、清晰AI交互的开发者及其他用户。

earthtojake/text-to-cad

JavaScript · ★ 9,030 · 🍴 1,021 · 📈 378 stars today

A collection of agent skills for CAD, robotics and hardware design

中文介绍 `text-to-cad` 汇集了一系列专门为计算机辅助设计（CAD）、机器人技术和硬件设计领域打造的AI代理技能。这些技能旨在通过自动化和智能化方式，辅助工程师和设计师处理从概念到实现过程中的复杂任务，例如基于文本生成CAD模型、优化机器人路径规划或辅助硬件布局。它能显著提升设计效率和精确性。

1jehuang/jcode

Rust · ★ 10,249 · 🍴 1,127 · 📈 835 stars today

The most intelligent agent harness for code

中文介绍 Jcode 是一个专为编码 Agent 设计的开发与评估框架（Coding Agent Harness）。该项目旨在为研究人员和开发者提供一套工具，用于构建、测试和比较 AI 编码助手的性能与能力。它能够帮助评估 AI 模型在代码生成、错误修复、重构以及其他编程任务中的表现。通过 Jcode，开发者可以更有效地迭代和优化 AI 驱动的编程工具，从而推动自动化编程和智能辅助编码技术的发展。

oblien/openship

TypeScript · ★ 6,044 · 🍴 435 · 📈 1,556 stars today

Self-hosted deployment platform

中文介绍 openship 是一个开源的自托管部署平台，旨在为开发者和运维团队提供一套完整的应用发布和管理解决方案。用户可以在自己的服务器或云基础设施上部署该平台，从而拥有对应用部署流程和数据的完全控制。它通常集成了版本控制、持续集成/持续部署（CI/CD）、环境管理、扩展和监控等功能，帮助团队实现自动化、高效的应用上线。适用于需要内部部署、注重数据主权或寻求替代商业部署服务的企业和个人。

AstrBotDevs/AstrBot

Python · ★ 37,429 · 🍴 2,607 · 📈 416 stars today

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

中文介绍 AstrBot 是一个多功能的 AI Agent 助手和开发框架，旨在简化跨平台智能助手的构建与部署。它深度集成了多种即时通讯（IM）平台、主流大语言模型（LLM）以及丰富的插件和 AI 功能。该项目提供了强大的扩展性，允许开发者根据需求定制 Agent 的行为和能力，并可作为 OpenClaw 等工具的开源替代方案。AstrBot 适用于需要构建在不同社交和办公平台上线，并能灵活响应用户请求的智能 AI 助手的开发者。

every-app/open-seo

TypeScript · ★ 6,519 · 🍴 709 · 📈 850 stars today

Open source alternative to Semrush and Ahrefs

中文介绍 open-seo 旨在成为 Semrush 和 Ahrefs 等商业 SEO 工具的开源替代品。它提供了一套免费且透明的解决方案，帮助网站管理员、营销人员和内容创作者进行关键词研究、竞争对手分析、网站审计及排名跟踪，从而优化搜索引擎表现。对于预算有限但又需要强大 SEO 功能的用户来说，open-seo 提供了一个极具吸引力的开源选择，助力网站提升自然搜索流量。

tradesdontlie/tradingview-mcp

JavaScript · ★ 4,789 · 🍴 2,170 · 📈 219 stars today

AI-assisted TradingView chart analysis — connect Claude Code to your TradingView Desktop for personal workflow automation

中文介绍 `tradingview-mcp` 项目旨在通过AI技术增强TradingView的图表分析能力。它允许用户将Claude Code AI模型集成到TradingView桌面版，从而实现个性化的交易工作流自动化。交易员和投资者可以利用此工具，自动执行市场数据分析、识别潜在交易模式或验证策略，显著提升分析效率和交易决策的响应速度。

AlexsJones/llmfit

Rust · ★ 30,135 · 🍴 1,840 · 📈 194 stars today

Hundreds of models & providers. One command to find what runs on your hardware.

中文介绍 `llmfit` 提供了一个便捷的解决方案，旨在帮助用户快速识别哪些大型语言模型（LLM）及其提供商能够在其现有硬件环境下高效运行。该项目整合了数百种模型和供应商信息，用户只需执行一个命令，即可轻松评估本地设备的兼容性。它极大地简化了LLM的选型与部署前测试流程，适用于LLM开发者、研究员或个人用户。

hyprwm/Hyprland

C++ · ★ 36,984 · 🍴 1,861 · 📈 88 stars today

Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.

中文介绍 `Hyprland` 是一个独立的、高度可定制的动态平铺式Wayland合成器。它在提供现代、高效窗口管理功能的同时，强调视觉美学，打破了传统平铺式管理器在外观上的刻板印象。项目为Linux用户提供了一个高性能、流畅且个性化极强的桌面环境体验，特别适合追求极致效率与美观兼顾的开发者和高级用户。

chrislgarry/Apollo-11

Assembly · ★ 69,872 · 🍴 7,836 · 📈 1,195 stars today

Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.

中文介绍 `Apollo-11` 项目收录了阿波罗11号任务中指令舱和登月舱制导计算机（AGC）的原始源代码。这份历史性代码不仅是早期航天工程的瑰宝，也展现了在极其有限的计算资源下，工程师如何编写出可靠且关键的飞行控制程序。它对于计算机历史研究者、软件考古学家及航天爱好者具有极高的参考和教育价值。

DioxusLabs/dioxus

Rust · ★ 37,598 · 🍴 1,772 · 📈 261 stars today

Fullstack app framework for web, desktop, and mobile.

中文介绍 `Dioxus` 是一个强大的全栈应用程序框架，使开发者能够使用一套代码库，轻松地为Web、桌面和移动平台构建高性能应用。它解决了多平台开发中代码复用性和维护成本的挑战，提供统一的开发体验。Dioxus 特别适合追求效率、希望利用Rust语言优势进行全栈开发的工程师和团队。

langchain-ai/open_deep_research

Python · ★ 12,194 · 🍴 1,738 · 📈 14 stars today

中文介绍 `open_deep_research` 是一个基于LangChain框架的项目，旨在探索和实现深度研究的自动化。它可能利用大型语言模型（LLM）进行信息收集、内容分析、观点提炼以及报告生成等任务，极大地提升研究效率。该项目适用于学术研究员、市场分析师、情报专家或任何需要进行大规模信息整合与洞察提取的专业人士。

diegosouzapw/OmniRoute

TypeScript · ★ 23,368 · 🍴 3,127 · 📈 2,040 stars today

Never stop coding. Free MIT AI gateway: one endpoint, 268+ providers (50+ free), 500+ models — Kimi, Claude, GPT, OpenAI, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A,

中文介绍 OmniRoute 提供一个免费的 AI 网关，通过单一 API 端点集成超过231个 AI 提供商（其中50余个免费），旨在解决多模型调用的复杂性。它支持将 Claude Code、Codex、Cursor、Cline、Copilot 等编码助手连接至免费的 Claude、GPT、Gemini 等主流大模型，大幅降低开发成本。项目还采用 RTK+Caveman 堆叠压缩技术，可节省 15-95% 的数据传输开销，适合开发者统一管理 AI 服务、优化性能并利用免费资源进行高效开发。

agegr/pi-web

TypeScript · ★ 1,690 · 🍴 275 · 📈 286 stars today

Web UI for the pi coding agent

中文介绍 `pi-web` 项目为 `pi coding agent` 提供了一个直观易用的Web用户界面。它旨在简化用户与AI编程代理的交互过程，摆脱命令行操作的复杂性，通过浏览器即可轻松部署、配置和管理agent，并查看其工作输出。此Web UI极大地提升了 `pi coding agent` 的可访问性和用户体验，适合各类开发者。

schollz/croc

Go · ★ 36,716 · 🍴 1,458 · 📈 396 stars today

Easily and securely send things from one computer to another 🐊 📦

中文介绍 `croc` 是一个高效且安全的文件传输工具，允许用户在任意两台计算机之间轻松发送文件。它通过命令行操作，支持点对点传输并默认进行加密，确保数据安全。`croc` 能够穿透防火墙，无需复杂的配置，解决了传统文件共享方案的诸多不便。适用于需要快速、私密地共享文件给其他设备或用户的场景。

microsoft/Ontology-Playground

TypeScript · ★ 1,974 · 🍴 243 · 📈 355 stars today

Free, open-source web app for learning about ontologies and Microsoft Fabric IQ. Explore a catalogue of pre-built ontologies, design your own visually, export as RDF/XML, and share interactive diagrams. Zero backend, fully static.

中文介绍 Ontology-Playground 是微软推出的一款免费开源 Web 应用，专为学习本体论（ontologies）和 Microsoft Fabric IQ 设计。它提供了一个互动平台，用户可以探索预构建的本体目录，通过直观的图形界面设计自己的本体结构，并将其导出为标准的 RDF/XML 格式。此外，用户还能分享生成的交互式本体图。该工具旨在降低本体论的学习门槛，并为数据架构师、知识工程师及对语义数据建模和知识图谱感兴趣的开发者提供一个实用的设计与可视化环境。

dottxt-ai/outlines

Python · ★ 14,788 · 🍴 797 · 📈 49 stars today

Structured Outputs

中文介绍 `outlines` 项目专注于为大型语言模型（LLM）提供结构化输出能力。它解决了LLM自由文本生成难以解析和利用的问题，确保模型输出严格遵循预定义的格式，如JSON、XML或特定语法结构。这极大地简化了LLM在自动化工作流、数据抽取或API集成中的应用，特别适合LLM应用开发者和数据工程师，以提升数据处理的准确性和效率。

Software Factories, Light and Dark

@addyosmani · 407.1K 粉丝 · 636.9K 阅 · 503 赞 · 49 转

07/21 13:43

A software factory is harnessed loops at scale. You can run the loop with humans in it (light factory): trading judgment and concentration against speed and breakage. Or you can ignore the humans

中文介绍 博主阐述了「软件工厂」概念，将其分为两种模式：由人类参与的「明工厂」（Light Factory），通过权衡判断力与速度；以及完全自动化、忽略人类参与的「暗工厂」（Dark Factory）。探讨了大规模软件开发中的不同策略与挑战。

How to Build a Self-Improving Outbound System on Codex

@nifinet · 11.0K 粉丝 · 337.0K 阅 · 518 赞 · 33 转

07/19 22:36

Earlier this year, Andrej Karpathy (@karpathy) pointed an agent at his own training code and let it run for two days. It ran 700 experiments, kept the 20 that beat the benchmark, and made the model

中文介绍 介绍如何构建一个自我改进的系统，灵感源于 Andrej Karpathy 的实验。Karpathy 让一个 agent 针对自身训练代码运行两天，执行了 700 次实验，并筛选出 20 个优于基准的成果。此方法展示了通过 AI agent 驱动的自动化实验，持续优化模型和代码的潜力。

GLM 5.2 With Vision

@part_harry_ · 1.5K 粉丝 · 225.6K 阅 · 503 赞 · 46 转

07/16 12:24

GLM 5.2 is one of the best currently available open source language models. However, unlike other flagship models like Qwen, Kimi and Minimax, GLM 5.2 does not support image inputs. We took this as a

中文介绍 博主讨论开源语言模型GLM 5.2的视觉能力（Vision），可能是在为其探索或开发图像输入功能。这一举措旨在增强GLM 5.2的多模态处理能力，使其能够处理视觉信息，从而拓宽应用范围并提升其在与Qwen、Kimi等模型竞争时的竞争力。

The Self-Driving Company

@amasad · 472.6K 粉丝 · 223.7K 阅 · 560 赞 · 65 转

07/17 01:07

We are beginning to see what happens when a company learns to operate itself. In the past six months, engineers at Replit have nearly tripled code output. Review times held steady. Reversions and

中文介绍 博主提出了「自驱动公司」这一概念，暗示企业运营未来将高度自动化，能像自动驾驶汽车一样自我管理和优化。这可能涉及利用AI和自动化技术，大幅提升公司的运营效率、决策速度和资源配置能力，预示着企业组织形态和生产力的一次重大变革。

Maybe Intelligence Ain't All That

@CliffordSosin · 16.4K 粉丝 · 197.0K 阅 · 514 赞 · 49 转

07/19 05:36

Superintelligence arrived. You probably didn't notice, because it turned out to be kind of incremental. Don't believe me? Run the test. Talk to Fable 5 for an hour, then talk to your ten smartest

中文介绍 博主探讨了「超级智能」的到来，指出其以渐进式而非颠覆性方式出现，因此可能未被察觉。他建议进行一项测试：与 Fable 5 交流一小时，再与十位最聪明的人交流，以感受这种「增量式超级智能」。

How OpenAI’s Sol Finally Learned Design Taste

@DesignArena · 17.6K 粉丝 · 191.5K 阅 · 509 赞 · 46 转

07/16 00:36

We benchmarked GPT-5.6 Sol on Design Arena’s Web Design (Non-Agentic) Arena, and we were surprised to find that it ranks 1st overall. This is 18 places higher than its predecessor GPT-5.5, and is the

中文介绍 DesignArena 提出了「How OpenAI’s Sol Finally Learned Design Taste」的问题，可能旨在探讨 OpenAI 的 Sol 模型在学习和掌握设计美学方面的进展和方法。

How to build your first team of agents:

@EXM7777 · 126.7K 粉丝 · 173.6K 阅 · 521 赞 · 51 转

07/18 21:48

I'm going to show you how to build your first team of AI agents... and how to wire them into a self improving loop inside a shared workspace the team we're building has 5 agents, one for each function

中文介绍 该推文详细讲解如何构建首个 AI 智能体团队，并将其整合到自我改进循环的工作流中。教程涵盖在共享工作空间内连接智能体的步骤，特别提到构建一个由 5 个具备独立功能的智能体组成的团队。

Graph Engineering with Claude: 14-Step roadmap from 0 to graph architect (Full Course)

@0xCodez · 23.9K 粉丝 · 154.5K 阅 · 510 赞 · 73 转

07/20 19:23

Most people who try to build a multi-step agent end up with a straight line. Step one, step two, step three - each waiting politely for the last to finish before it starts. 9/10 notice that half those

中文介绍 博主分享利用 Claude 进行「图工程」的 14 步路线图，旨在解决构建多步骤 agent 时常见的线性执行问题。许多人在设计 agent 时常陷入简单串联模式，而此教程将展示如何从零开始，通过图工程方法构建更复杂、非线性的 AI agent 工作流。

The Next Horizon in Agents

@btaylor · 158.6K 粉丝 · 144.3K 阅 · 511 赞 · 40 转

07/16 22:48

Introducing Horizon Today, Sierra is announcing Horizon, a platform that enables agents to pursue long-horizon goals, like originating a loan or getting prior authorization for a healthcare procedure.

中文介绍 Sierra公司发布了名为Horizon的新平台，旨在赋能AI Agent处理复杂且「长周期」的实际业务目标。该平台支持Agent完成如发起贷款或获取医疗程序预授权等多步骤任务。这标志着AI Agent从执行短期指令向处理更深层次、更具商业价值的复杂流程迈进，为企业自动化提供了新的可能性。

Gemini API Managed Agents: free tier, triggers & more

@GoogleAIStudio · 186.6K 粉丝 · 111.0K 阅 · 512 赞 · 51 转

07/17 01:05

Today we’re announcing new capabilities for Managed Agents in Gemini API, including free tier availability, budget control guardrails, and scheduled triggers. Building on our previous release of

中文介绍 Google AI Studio宣布Gemini API的Managed Agents新增功能，包括提供免费层级、预算控制保护措施以及支持定时触发器。这些更新建立在之前的发布基础上，旨在降低开发者使用门槛，赋予他们更大的灵活性来管理和部署AI Agent。新功能将促进更广泛的Agent应用，并帮助用户更好地控制成本与调度。

How we built our knowledge base

@cerebras · 60.4K 粉丝 · 70.7K 阅 · 509 赞 · 38 转

07/17 02:27

Authors: @hi_im_isaac_, @learnwdaniel, @gaozenghao note: the interactive version of full technical blog available: https://www.cerebras.ai/blog/how-we-built-our-knowledge-base Employees ask our internal knowledge base more than 15,000

中文介绍 Cerebras发布技术博客，详细阐述了他们如何构建企业内部知识库。该知识库每月处理员工超过15,000次的查询，极大提高了工作效率。博文由多位作者共同撰写，提供了实际案例和技术细节，为其他组织构建高效智能知识管理系统提供了宝贵的实践经验和设计思路。

Kimi K3 on KernelBench

@elliotarledge · 40.7K 粉丝 · 69.3K 阅 · 506 赞 · 45 转

07/17 17:24

This is the Kimi K3 post you guys have been waiting for. I got some early access to this model and have been testing it on kernels, and even before seeing the benchmark scores I was impressed with its

中文介绍 博主获得了Kimi K3模型的早期访问权限，并对其进行了初步测试和KernelBench基准评估。在未查看具体分数前，博主已对Kimi K3的性能印象深刻。这篇分享为期待Kimi K3的用户提供了第一手体验和性能洞察，预示着该模型可能在某些任务上展现出强大的能力。

Kimi K3 Reverse Engineering - Opus Without The Nagging

@herrcore · 15.4K 粉丝 · 64.2K 阅 · 514 赞 · 84 转

07/20 03:28

tl;dr K3 makes us question why we are paying Anthropic. We’ve been using Opus as our go-to model for reverse engineering tasks since the release of 4.5, and with each new release, it feels like we

中文介绍 博主对 Kimi K3 进行了逆向工程任务评测，并与 Anthropic 的 Opus 模型对比。评测结果表明，Kimi K3 在此类任务中表现出色，甚至让博主质疑继续为 Opus 付费的必要性。这暗示 Kimi K3 可能是逆向工程领域中，一个性能与性价比俱佳的替代方案。

Let's build Claude Code's harness (step-by-step)

@akshay_pachaar · 281.7K 粉丝 · 53.7K 阅 · 516 赞 · 74 转

07/16 02:10

We will cover everything that goes into building a coding harness, the agent loop, planning, subagents, sandboxing, memory, and checkpointing, built step by step. If you've ever tried building your

中文介绍 博主分享了为 Claude Code 构建编码辅助工具「coding harness」的逐步教程。内容深入讲解了智能体循环、规划、子智能体、沙盒环境、内存管理和检查点等关键技术组件的实现细节。

From Loop Engineering to Graph Engineering?

@IntuitMachine · 62.3K 粉丝 · 50.7K 阅 · 552 赞 · 47 转

07/18 18:00

What the shift in AI agent architecture is really about Peter Steinberger just posted nine words that gathered thousands of likes: https://x.com/steipete/status/2078277297791189132 "Are we still talking loops or did we

中文介绍 该推文探讨了 AI 智能体架构的关键转变，从传统的「循环工程」（Loop Engineering）转向「图工程」（Graph Engineering）。文章引用 Peter Steinberger 的热门观点，提出对当前智能体设计范式的深刻反思。

How I use Linear to manage agents (and why we should all be building software factories)

@enginoid · 1.1K 粉丝 · 49.9K 阅 · 522 赞 · 37 转

07/19 22:31

Linear is probably my best-value subscription at the moment. I pay the sole user fee of $12/mo and the company agents have eaten through ~400 issues in the past month. I use Linear to organize my

中文介绍 博主分享如何利用项目管理工具 Linear 管理 AI agent 的工作流。他每月支付 $12 订阅费，其公司 agent 在过去一个月内处理了约 400 个问题。该分享展示了将 Linear 与 AI agent 结合以大幅提升生产力的方法，并倡导构建「软件工厂」的理念。

How to build a self-improving code review agent

@zachlloydtweets · 12.1K 粉丝 · 42.7K 阅 · 527 赞 · 57 转

07/16 00:20

This is the third post in my series on how to build a cloud software factory: Build an issue triage agent Build a spec writing agent [This post] Build a self-improving code review agent I’ll describe

中文介绍 该推文是关于构建「云软件工厂」系列文章的第三部分，核心内容是如何搭建一个自我改进的代码审查 agent。博主将详细描述其构建过程。此前系列文章已涵盖问题分类 agent 和规范编写 agent，本次分享进一步完善了自动化软件开发的工作流。

How Anthropic runs large-scale code migrations with Claude Code

@ClaudeDevs · 614.2K 粉丝 · 40.3K 阅 · 689 赞 · 40 转

07/22 03:47

Code migrations, projects that port a production codebase to a new language, were multi-year endeavors until recently. In the last month, individual developers at Anthropic migrated 10 code packages

中文介绍 Anthropic 团队分享了如何利用 Claude Code 大幅加速代码迁移项目。此前耗时多年的大规模生产代码库迁移，现在通过 Claude Code 的辅助，单个开发者在一个月内即可完成 10 个代码包的移植，极大地提升了效率。

What does a modular Agent Operating System do?

@unicity_labs · 119.9K 粉丝 · 13.1K 阅 · 525 赞 · 289 转

07/20 17:31

Unicity AOS is at its core a fixed Rust microkernel that enforces security, cost, and approval controls below your agent code, and signs every action into a tamper-evident audit chain. It runs

中文介绍 Unicity Labs 介绍了其模块化 Agent 操作系统 Unicity AOS。该系统核心是基于 Rust 的微内核，负责在 Agent 代码层之下强制执行安全、成本和审批控制，并将每项操作签署到防篡改的审计链中，确保 AI Agent 行为的可控性与透明度。

Did you have a good weekend? Wonderful. Meet Axxon One

@therealDeFlock · 82.7K 粉丝 · 12.2K 阅 · 500 赞 · 120 转

07/20 08:08

"Axxon One supports automatic tracking of people as they move between cameras". "automatic tracking of people"... Ideal for logistics, warehousing, and Safe City projects, this AI detector

中文介绍 博主介绍了 AI 产品 Axxon One。该产品支持「跨摄像头对人员进行自动追踪」，并配备 AI 探测器。它尤其适用于物流、仓储以及智慧城市等项目，旨在为这些领域提供高效且自动化的监控与人员追踪解决方案，以提升运营效率和安全性。

FlowMimic: Mask-free Visual Editing and Generation with Pixel-pair Warped Flow Field for Online Video Editing Data Generation and Modality Mimicry

👍 23

07/20 08:00

In line with the prevailing direction of vision research, we explore the integration of both generation and editing capabilities for video and image modalities within a single model. Current approaches to collecting video editing data typically depend on labour-intensive, time-consuming curated proc

中文介绍 FlowMimic模型采用像素对扭曲流场技术，实现了无遮罩的视频和图像生成与编辑，将这两种能力整合于单一模型中。该方法旨在克服当前视频编辑数据收集费时费力的问题，提升在线视频编辑数据生成的效率与质量。

HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement

👍 46

07/20 08:00

Human-object centric video personalization (HOCVP) is a core task within subject-driven video generation. However, existing methods suffer from two key limitations. First, most approaches focusing on inter-subject personalization still struggle to strike a balance between high subject fidelity and a

中文介绍 HOMIE提出一种多模态智能增强方法，旨在解决以人-物为中心的视频个性化（HOCVP）任务在主体驱动视频生成中的挑战。现有方法在保持高主体保真度与生成多样性之间难以平衡，HOMIE致力于通过多模态融合改进此项核心任务。

SWE-Pruner Pro: The Coder LLM Already Knows What to Prune

👍 64

07/20 08:00

Pruning long context for coding agents has been a vital technology for efficient context management. While existing context pruning methods such as SWE-Pruner realize this by attaching a separate code classifier, we find the agent itself encodes internal representations indicating the relevance of c

中文介绍 论文介绍SWE-Pruner Pro，一种面向编码智能体的长上下文剪枝方法。不同于现有方法（如SWE-Pruner）依赖独立的分类器，SWE-Pruner Pro发现编码大语言模型（LLM）自身已包含指示何处应剪枝的内部表示，从而实现更高效的上下文管理。

FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications

👍 3

07/20 08:00

Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose efficient deployment requires application-specific decisions about placement, streaming, and intra-model parallelism. Existing serving systems and auto-parall

中文介绍 FlashRT是一个智能体引导框架，旨在指导智能体高效部署实时多模态应用，如语音助手和交互式视频生成。这类应用将异构模型组合成流水线，其高效部署需要关于部署位置、数据流和模型内并行性的决策，FlashRT旨在优化这些决策。

jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation

👍 0

07/20 08:00

Listwise rerankers are the discriminative core of agentic retrieval pipelines, yet production deployment demands efficiency, domain robustness, and fluency on semi-structured data at the same time. We present jina-reranker-v3.5, a 0.6B-parameter listwise reranker that meets these demands together wi

中文介绍 论文介绍jina-reranker-v3.5，这是一个拥有0.6B参数的高效列表式重排序器。该模型结合了混合注意力机制和自蒸馏技术，旨在满足生产环境中对智能体检索流水线在效率、领域鲁棒性以及半结构化数据处理流畅性方面的严苛要求。

Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices

👍 0

07/20 08:00

Real-time EEG classification on edge devices is bottlenecked by the floating-point arithmetic of conventional neural networks. We investigated Differentiable Logic Gate Networks (Diff-Logic) as a hardware-native alternative that compiles models into pure Boolean circuits executable via bitwise CPU o

中文介绍 为解决边缘设备上实时脑电图（EEG）分类受传统神经网络浮点运算瓶颈的限制，研究人员提出了可微逻辑门网络（Diff-Logic）。该技术作为一种硬件原生替代方案，能将模型编译为纯布尔电路，从而在边缘设备上实现低延迟的EEG分类。

Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints

👍 12

07/20 08:00

Structure-based drug design (SBDD) leverages the 3D structure of protein targets, often complemented by other spatial constraints, to generate candidate binding molecules. While diffusion models have dominated as a leading paradigm for high-quality 3D molecule generation, LLM-based methods are rapid

中文介绍 结构药物设计（SBDD）利用蛋白质靶标的3D结构及空间约束来生成候选结合分子。尽管扩散模型在高质量3D分子生成中占主导地位，但该研究探讨并基准测试了基于大语言模型（LLM）的方法在空间约束下生成结合分子的潜力。

O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning

👍 8

07/20 08:00

Industrial Video Anomaly Detection (IVAD) aims to identify anomalous objects and events in an industrial process, which is crucial for modern manufacturing and quality control systems. Existing VLM-based anomaly reasoning methods are capable of detecting open-ended anomalies in general domains. Howe

中文介绍 O-VAD提出一种通过以物体为中心的跟踪与推理，实现工业视频异常检测（IVAD）的方法。IVAD对于现代制造和质量控制系统至关重要，旨在识别工业流程中的异常物体和事件。现有基于VLM的异常推理方法在开放式异常检测方面存在局限。

LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks

👍 8

07/20 08:00

Reinforcement learning (RL) on open-ended tasks compresses an LLM's rubric-based evaluation into a scalar reward, discarding rich textual feedback and conflating responses with distinct quality profiles. We propose Experiential Learning (EL), which repurposes the feedback model from an LLM-as-a-Judg

中文介绍 针对不可验证任务，论文提出“大语言模型（LLM）作教练”的经验学习（EL）范式。传统强化学习将LLM的丰富文本反馈压缩为标量奖励，可能丢失关键信息。EL方法旨在重新利用反馈模型，以更有效的方式处理开放式任务，提升LLM在复杂任务上的表现。

WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting

👍 2

07/20 08:00

Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available. We present WorldCupArena, a dynamic benchmark for language models and deep-research agents. The 2026 FIFA World Cup is

中文介绍 WorldCupArena是一个动态基准测试平台，用于细粒度评估大语言模型和深度研究智能体在足球赛事预测方面的能力。足球预测不仅需要历史数据，还需要模型处理实时变化的信息并在赛前做出明确判断。WorldCupArena涵盖了20XX年世界杯数据。

VGOcc: Learning Visual-Geometric Gaussians for Vision-Centric 3D Driving Occupancy Prediction

👍 0

07/20 08:00

Vision-only occupancy prediction requires recovering a semantic 3D occupancy field from calibrated surround-view images, where each view provides observations with ambiguous depth along camera rays. Existing methods have progressed from dense structured representations to sparse Gaussian primitives,

中文介绍 VGOcc提出了一种学习视觉几何高斯的方法，用于以视觉为中心的3D驾驶占位预测。该任务旨在从校准的全景图像中恢复语义3D占位场。由于每个视角沿相机光线提供的深度信息模糊，VGOcc在此基础上进行优化，以提升预测准确性。

Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

👍 3

07/20 08:00

Self-hosted AI agents read and write their own memory and configuration files to function. An agent may get compromised via corruption of its own state -- a compromise realized via legitimate OS system call invocation. We refer to this class of threats as self-state attacks. In this paper, we invest

中文介绍 论文探讨了针对自托管AI智能体的“自状态攻击”，即通过合法操作系统调用，利用智能体读取和写入自身内存及配置文件的机制，破坏其内部状态进而实现攻击。研究旨在评估操作系统防御措施在抵御此类威胁方面的有效性与局限性。

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

👍 32

07/20 08:00

We present RynnBrain 1.1, a family of embodied foundation models spanning 2B, 9B, and 122B-A10B scales. Trained with a unified spatio-temporal and physically grounded framework, RynnBrain 1.1 supports embodied perception, spatial reasoning, localization, and planning. Compared with RynnBrain 1.0, it

DiFA: Inference-Time Forward-Process Alignment for Diffusion Models

👍 2

07/20 08:00

The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact estimator, neglecting the inherent statistical uncertainty of the denoising process. In this work, we propose Forward-Proces

Aggregate in the Advantage, Not the Ratio: A Canonical-Form Analysis of Cooperative Multi-Agent Policy Optimization

👍 0

07/20 08:00

Multi-agent policy optimization, exemplified by PPO-based methods, is a key branch of cooperative Multi-Agent Reinforcement Learning (MARL). A central design question is how many neighboring agentsIn this paper, "neighbors" refer not only to physical proximity but also to agents whose actions influe

ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video

👍 2

07/20 08:00

Egocentric devices, such as wearable front-facing cameras, provide a unique perspective for capturing the continuous interaction between a human viewer and the surrounding environment. A holistic and efficient multimodal model capable of reconstructing this 4D representation is therefore highly desi

FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches

👍 1

07/20 08:00

We introduce WC2026-Agents, a benchmark and dataset for evaluating large language models (LLMs) as autonomous forecasting agents on real, future events. For every one of the 104 matches of the 2026 FIFA World Cup, four frontier models -- Claude Opus 4.8, ChatGPT (GPT-5.5, high reasoning), Gemini 3.1

MagicSelector: Joint Optimization for Agent Tool Selection via Counterfactual Decomposition and Progressive Reranking

👍 0

07/20 08:00

We present MagicSelector, a joint optimization framework integrating Counterfactual task decomposition, Progressive reranking, and Dynamic Top-K, designed to address the fundamental challenges of tool retrieval in agents. MagicSelector is a specialized framework capable of translating ambiguous user

ShotPlan: Cinematic Video Generation with Learnable Planning Token

👍 3

07/20 08:00

Current video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic video generation, where coherent narratives and effective multi-shot composition require explicit shot planning. To address this challenge, we propose ShotPlan, a framework for expli

Hierarchy-Aware and Anatomy-Guided Learning for Lung Ultrasound Video Classification

👍 0

07/20 08:00

Lung ultrasound (LUS) is a bedside tool for assessing pulmonary edema in patients at risk due to heart failure or impaired kidney function. However, automated LUS analysis remains challenging because of speckle noise, imaging artifacts, and operator-dependent acquisition variability. In this work, w

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

👍 4

07/20 08:00

We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is that by training the model to distinguish good and bad tokens in a response, we naturally guide the model towards generati

Thinking in Video: Can Video Generators Really Reason About the Real World?

👍 0

07/20 08:00

Recent advances in world models and video generation have given rise to an emerging reasoning paradigm that leverages video generative models to simulate, predict, and reason about real-world dynamics. We redefine this paradigm as Thinking in Video, where video is not merely an output artifact but a

StructGen: Disambiguating Multi-Reference Image Generation via Structured Context Modeling

👍 0

07/20 08:00

Multi-reference image generation aims to synthesize images by integrating attributes from multiple reference images under textual instructions. As the number of references increases, the task necessitates complex semantic comprehension, such as correctly associating attributes with the intended subj

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation

👍 2

07/20 08:00

Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome: it can renegotiate, report the failure honestly, coerce the subordinate, or lie about the result. No benchmark measures which of these an uninstructed model

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

👍 139

07/19 08:00

Video multimodal large language models (MLLMs) can describe what happens in a video, but rarely identify when the supporting evidence occurs. We study generalist video temporal grounding, in which one model predicts a variable-cardinality set of evidence intervals across video lengths, domains, quer

Quantifying Diversity of Thought: A Predictive Law of Weighted LLM Ensemble Lift

👍 0

07/19 08:00

This paper provides an experimentally verified formal law for calculating the uplift that diversity of thought provides in Large Language Model (LLM) ensembles. From first principles, we derive an exact decomposition of LLM ensemble lift into rescue and damage masses, which yields a compact heuristi

STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognition

👍 0

07/19 08:00

Understanding physical human-robot and human-human interactions is a challenging yet emerging topic in 3D vision. While most existing methods rely on skeleton sequences--effective in low-light and privacy-sensitive environment--they face two major challenges: 1) learning and effectively exploiting i

EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World

👍 73

07/19 08:00

This paper introduces EvolvingWorld, a framework and benchmark for character and world co-evolution in interactive literary worlds. Existing systems either treat interactive literary simulation as static persona imitation or isolated scene generation, failing to capture how characters and worlds evo

Distilled Reinforcement Learning for LLM Post-training

👍 6

07/19 08:00

Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credi

The Geometry of Semantic Space: A Continuous Geometric Framework for the Transformer Architecture

👍 4

07/19 08:00

We present a continuous geometric framework that models the discrete algebraic operations of the Transformer architecture as an integro-differential equation (IDE) on a semantic fiber bundle calE = calM times R^d. Beginning from a single geometric axiom -- that the token sequence forms a discrete 1-

ditto.site

07/22 04:56

Clone any website into clean code. Free & open source

中文介绍 ditto.site 是一款免费开源的网站克隆工具，旨在帮助用户将任何现有网站转换为结构清晰、易于维护的干净代码，以提升开发效率和代码质量。

Routine AI

07/22 04:56

Control work with your voice. The Siri for work.

中文介绍 Routine AI 是一款面向工作场景的语音控制工具，旨在通过语音指令帮助用户管理工作，类似"工作版 Siri"，提高日常工作效率。

PieceKeeper

07/22 04:56

Track your music repertoire and practice

中文介绍 PieceKeeper 是一款专为音乐家设计的工具，可以帮助用户跟踪其音乐曲目库和日常练习进度，以系统化管理音乐学习与提升。

Diffsmith

07/22 04:56

Comment on your AI agent's code & collaborate on changes

中文介绍 Diffsmith 是一款代码审查工作室，允许用户对 AI 智能体生成的代码进行评论，并与团队成员协作修改，从而优化 AI 模型的代码质量和协同开发流程。

Routebase

07/22 04:56

Catch API drift before your customers do

中文介绍 Routebase 旨在帮助开发者在用户发现问题之前，识别并解决 API 接口的变化或"漂移"问题，确保 API 的稳定性和用户体验。

Phantomstory

07/22 04:52

Launch a third-party blog to win AEO with just two clicks

中文介绍 Phantomstory 是一款工具，允许用户通过简单的两步操作，快速启动第三方博客，旨在帮助其网站在答案引擎优化（AEO）中取得优势，提升内容可见性。

Bolna Agent Studio

07/22 04:52

Build Voice AI Agent in 10 Minutes

中文介绍 Bolna Agent Studio 是一个平台，使用户能够在短短 10 分钟内快速构建语音 AI 智能体。该工具旨在简化语音 AI 应用的开发流程。

Lev8

07/22 04:50

Find, research, and reach the right people

中文介绍 Lev8 是一款旨在帮助用户寻找、研究并接触到目标人群的工具。它适用于销售、招聘或人际网络拓展等场景，提高用户触达关键联系人的效率。

Jockey by TwelveLabs

07/22 04:48

The video AI agent that understands your whole library

中文介绍 Jockey 是 TwelveLabs 推出的一款视频 AI 智能体，它能够理解并分析用户整个视频库的内容。该工具旨在提升视频内容的搜索、管理和利用效率。

CreateOS Sandbox

07/22 04:48

Instant, hardware Isolated Sandboxes for AI agents

中文介绍 CreateOS Sandbox 旨在为 AI 智能体提供即时且硬件隔离的沙盒环境。这有助于开发者安全地测试和部署 AI 模型，确保其运行的独立性和稳定性。

Devin AI: The Full Beginner’s Guide (Better Than Claude Code?)

07/17 02:25

中文介绍 这则YouTube视频提供了Devin AI的全面初学者指南，深入探讨了这款人工智能工具在代码开发方面的应用潜力。视频可能通过演示和比较，向观众展示Devin AI的功能和使用方法，并讨论其与Claude Code相比的优劣，以帮助初学者快速掌握。

Director by OpenArt

07/17 02:12

中文介绍 这则YouTube短视频介绍了OpenArt公司推出的一款名为「Director」的新产品或功能。该视频可能简要展示了「Director」的主要特点和用途，暗示其可能是一款用于创意或艺术领域的人工智能工具。

Codex and Claude Shipped Browser Updates. This Changes Everything.

07/15 21:00

中文介绍 Codex和Claude两大AI模型近期发布了浏览器更新，预计将对用户与AI的互动方式产生显著影响。这些更新可能包括功能改进、性能优化或更深度的浏览器集成，旨在提升用户体验并拓宽AI工具的应用场景。

OpenAI Just Merged ChatGPT and Codex. This Changes Everything.

07/13 01:24

Grok 4.5 + Cursor: Full Guide

07/10 01:51

Build Amazing Websites with Claude Fable 5 (Full Guide)

07/07 01:37

How to Create Your Own AI Assistant (It's So Easy)

07/01 09:40

Poweful Agents inside Slack

06/25 06:39

AI Agents Just Changed Forever: GLM 5.2, Codex Skills, Claude & Cursor

06/21 21:30

9 AI Agent Skills To Get Ahead of 99% of People

06/18 10:27

有点好奇，大家在 Codex 送重置的时候都蹬出了啥呢？

07/21 21:33

6 回复 · 程序员 节点

感觉又慢又贵：实测 Kimi-K3 编码能力

07/21 21:14

7 回复 · 程序员 节点

请问： Linux 系统下，有没有好用的 [查找重复文件] 的软件？

07/21 13:37

22 回复 · Linux 节点

求购或者有偿用一次 dayone plus 账号

07/20 21:54

17 回复 · Apple 节点

土区 App Store 内购方式的 Youtube Premium 被暂停， renew 要求绑定支付方式

07/20 14:17

35 回复 · Apple 节点

土区内购家庭组 YouTube，现要求添加付款方式或手机号，大佬指点下

07/20 11:08

9 回复 · Apple 节点

iPhone 无法批量导出视频是什么鬼？

07/20 06:59

6 回复 · Apple 节点

iOS 如何设置能实现像安卓手机的来电提醒一样显示是谁打电话过来的，比如 10086 标识为中国移动这样？

07/19 11:28

15 回复 · Apple 节点

iPhone 换电池，都是去官方还是自己买电池换呢？

07/18 20:19

23 回复 · Apple 节点

强烈推荐一款性价比极高的 Linux 本搞 vibe coding

07/17 12:24

33 回复 · Linux 节点

Mickey Mouse Sells a Bundle

07/22 04:48

4 points · 0 comments

OpenAI and Hugging Face partner to address security incident

07/22 04:09

153 points · 62 comments

'VPNs are lawful technical tools,' says EU Court in landmark copyright ruling

07/22 03:43

109 points · 13 comments

Advertise in ChatGPT

07/22 02:58

186 points · 194 comments

The Price of Happiness

07/22 02:42

25 points · 8 comments

Slater – Low-memory graphdb designed for read-heavy graphs

07/22 02:39

16 points · 6 comments

FreeInk: Open ecosystem for e-readers

07/22 02:39

219 points · 51 comments

AI Agent – TRMNL

07/22 02:32

20 points · 14 comments

Apple has decided to compete for creativity app users

07/22 02:30

56 points · 37 comments

Show HN: A self-running space economy SIM in Rust and Bevy

07/22 02:29

I built this with Claude cause I always wanted to tinker with a simulation economoy and I love space themes.A space-economy sim where nothing is scripted. A few hundred autonomous ships each run their own planner. Some chase the best trade route, take a delivery contract, refuel, retrofit at a shipy

Cheap self-hosted Kubernetes on Hetzner cloud (2025)

07/22 02:25

50 points · 26 comments

Greedy is optimal for single-pass semi-streaming matching

07/22 01:59

14 points · 0 comments

Apple Private Cloud Compute SoC 3 audit reports

07/22 01:58

55 points · 13 comments

Laguna S 2.1

07/22 01:17

112 points · 24 comments

Jack Dorsey launches Buzz to combine team chat, AI agents and Git hosting

07/22 01:14

https://x.com/jack/status/2079605800998146171, https://xcancel.com/jack/status/2079605800998146171https://buzz.xyz/

Show HN: CodeAlmanac – Karpathy-style codebase wiki from your conversations

07/22 01:12

Hey HN! This is Divit from Almanac (YC S26). We built CodeAlmanac, a wiki for your coding agents that updates as you talk to them. It is open-source, local, and free.Here’s a demo: https://www.youtube.com/watch?v=XNQWV3TFBWMYour CC/Codex conversations contain a LOT of knowledge t

Meta's AI models are powering the first wave of Genesis Mission projects

07/22 01:03

https://www.energy.gov/undersecretaryforscience/genesis-miss...

Bloomy (YC S26) is hiring a founding engineer

07/22 01:00

About BloomyBloomy is an AI tutor and curriculum for K-12 students. Our student users are learning approximately 2x faster in early pilots, and students and teachers alike love our product.How it works: We diagnose students’ skill gaps, map out a personalized learning path for them, and then have an

The World's 2,400 Castles

07/22 00:05

139 points · 102 comments

France's Anssi Will Block PQC-Free Products from Certification Starting 2027

07/22 00:02

71 points · 31 comments

Long presumed dead, a thriving coral reef is discovered in West Africa

07/21 23:41

https://www.frontiersin.org/journals/marine-science/articles...

Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

07/21 23:17

https://console.cloud.google.com/agent-platform/publishers/g...

Apple defeats liability for not scanning iCloud for CSAM

07/21 22:31

254 points · 226 comments

PCjs Machines

07/21 21:48

160 points · 18 comments

Qwen-Image-3.0: Rich Content, Authentic Details, Deep Knowledge

07/21 16:44

507 points · 206 comments

Show HN: Read the Tape – Wordle for daytrading, five blind S&P 500 charts a day

07/20 20:07

Read the Tape gives players the same 5 S&P500 stock charts per day to predict. You select low, medium or high confidence and then call the chart UP or DOWN. It's a 1d chart which then resolves over 5 days. Alpha is scored against the Monkey Index, a basket of 11 random coin flips at low con

My USB Drive Has a Hidden Encrypted Vault

07/20 14:09

108 points · 67 comments

The unreasonable difficulty of time series forecasting

07/19 02:09

89 points · 30 comments

Zero-dependency streaming tar parser and writer for JavaScript

07/18 20:05

7 points · 0 comments

Show HN: Justif – Knuth-Plass justification and microtypography for the web

07/17 20:47

Justif is a drop-in JavaScript library that progressively enhances web pages to TeX-level text justification. Installation is a single <script> line, standard text and accessibility affordances are unchanged, and users with JS disabled get native browser rendering.I made justif because I'

v2.1.216

07/21 06:14

What's changed Added sandbox.filesystem.disabled setting to skip filesystem isolation while keeping network egress control Fixed a slowdown in long sessions where message normalization cost grew quadratically with the number of turns, causing multi-second stalls and slow resumes Fixed auto mode deny

中文介绍 Claude Code发布了v2.1.216版本。此更新引入了“sandbox.filesystem.disabled”设置，允许在保持网络出口控制的同时跳过文件系统隔离。同时，该版本修复了长时间会话中的性能下降问题，解决了消息标准化成本随轮次呈二次增长，导致多秒卡顿和恢复缓慢的现象。

v2.1.215

07/19 10:56

What's changed Claude no longer runs the /verify and /code-review skills on its own; invoke them with /verify or /code-review when you want them

中文介绍 Anthropic公司旗下Claude代码工具发布v2.1.215版本更新。此次更新调整了"/verify"和"/code-review"技能的运行方式，它们不再自动执行，用户需要时需通过指令明确调用。

v2.1.214

07/18 09:20

What's changed Fixed single-segment dir/** allow rules like Edit(src/**) auto-approving writes to nested dir/ directories anywhere in the tree instead of only /dir Fixed a permission-check bypass affecting commands run in Windows PowerShell 5.1 sessions Fixed Bash permission checks to fail closed on

中文介绍 Anthropic Claude Code发布了v2.1.214版本。此更新主要修复了多项错误，包括单段目录通配符允许规则、影响Windows PowerShell 5.1会话的权限检查绕过问题，以及Bash权限检查错误。

v2.1.212

07/17 08:26

What's changed /fork now copies your conversation into a new background session (its own row in claude agents) while you keep working; the in-session subagent it used to launch is now /subtask Added claude auto-mode reset to restore the default auto-mode configuration, with a confirmation prompt (pa

v2.1.211

07/16 07:02

What's changed Added --forward-subagent-text flag and CLAUDE_CODE_FORWARD_SUBAGENT_TEXT environment variable to include subagent text and thinking in stream-json output Fixed permission previews relayed to chat channels not neutralizing bidirectional-override, zero-width, and look-alike quote charac

v2.1.210

07/15 07:45

What's changed Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck Added a startup warning for Write(path), NotebookEdit(path), and Glob(path) permission rules — use Edit(path) or Read(path) instead Fixed isolation: 'w

v2.1.209

07/14 14:36

What's changed Fixed /model and other dialogs being blocked in claude agents background sessions (reverts an overly broad guard)

v2.1.208

07/14 09:10

What's changed Added screen reader mode: opt-in plain-text rendering for screen reader users. Run claude --ax-screen-reader, set CLAUDE_AX_SCREEN_READER=1, or add "axScreenReader": true to settings. Added vimInsertModeRemaps setting: map two-key insert-mode sequences like jj to Escape in vim mode Ad

v2.1.207

07/11 08:52

What's changed Auto mode is now available without CLAUDE_CODE_ENABLE_AUTO_MODE opt-in on Bedrock, Vertex AI, and Foundry; disable via disableAutoMode in settings Fixed the terminal freezing and keystrokes lagging while streaming responses containing very long lists, tables, paragraphs, or code block

v2.1.206

07/10 09:45

What's changed Added directory path suggestions to /cd, matching /add-dir behavior Added a /doctor check that proposes trimming checked-in CLAUDE.md files by cutting content Claude could derive from the codebase /commit-push-pr now auto-allows git push to the repo's configured push remote (remote.pu