Python · ★ 74,108 · 🍴 10,579 · 📈 1,937 stars today
利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.
中文介绍 基于 AI 大模型的一键短视频生成工具，用户只需输入主题关键词，系统自动完成文案撰写、素材匹配、语音合成和字幕添加，最终输出高清短视频。适合内容创作者、自媒体运营者快速批量生产视频内容，大幅降低短视频制作门槛和时间成本。
Python · ★ 134,905 · 🍴 9,226 · 📈 2,798 stars today
Python tool for converting files and office documents to Markdown.
中文介绍 微软开源的 Python 工具，可将 Word、Excel、PowerPoint 等 Office 文档及多种文件格式批量转换为 Markdown。适用于需要将文档内容接入 LLM 处理流水线、构建知识库或文档自动化处理的开发者，解决了 Office 文档与纯文本生态之间的格式鸿沟。
Python · ★ 56,586 · 🍴 5,487 · 📈 606 stars today
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
中文介绍 自适应 Web 爬虫框架，能够自动应对网页结构变化，支持从单次 HTTP 请求到大规模全站爬取的全场景覆盖。内置反检测、动态渲染等能力，开发者无需手动维护选择器即可稳定抓取数据，适合数据采集、竞品监控、内容聚合等场景。
Python · ★ 9,952 · 🍴 1,369 · 📈 357 stars today
Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!
中文介绍 Hermes Agent 的 Web 前端界面，让用户通过浏览器或手机直接与 Hermes 智能代理交互，无需命令行操作。提供友好的对话式 UI，适合希望在移动端或非技术环境下使用本地 AI Agent 能力的用户，降低了 Hermes 的使用门槛。
TypeScript · ★ 18,694 · 🍴 1,408 · 📈 251 stars today
Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more
中文介绍 Compound Engineering 官方插件，兼容 Claude Code、OpenAI Codex、Cursor 等主流 AI 编程工具。通过统一的插件接口将复合工程方法论集成进开发者现有工作流，适合在多种 AI 编码环境中保持一致的工程规范和最佳实践。
TypeScript · ★ 19,722 · 🍴 67,286 · 📈 27 stars today
The open-source repo for docs.github.com
中文介绍 docs.github.com 官方文档的开源仓库，包含 GitHub 全套产品的使用指南、API 参考和操作手册。开发者和技术写作者可在此提交 PR 贡献文档修正或补充，是参与 GitHub 生态建设、了解平台功能细节的重要参考来源。
Python · ★ 23,495 · 🍴 2,716 · 📈 635 stars today
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
中文介绍 OpenBMB 推出的无 Tokenizer 多语言文本转语音（TTS）模型 VoxCPM2，支持多语言语音生成、创意音色设计和高保真声音克隆。去除传统 Tokenizer 依赖使其更易扩展到低资源语言，适合语音合成研究者及需要高质量多语言 TTS 能力的语音应用开发者。
HTML · ★ 4,587 · 🍴 648 · 📈 323 stars today
A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use.
中文介绍 元技能框架，能够根据特定业务领域自动设计 Agent 团队结构、定义各专业 Agent 的职责边界，并生成相应的技能集合。适用于需要快速搭建多 Agent 协作系统的工程师，解决了多 Agent 系统设计复杂、难以标准化的问题。
Jupyter Notebook · ★ 2,945 · 🍴 441 · 📈 626 stars today
A straightforward method for training your LLM, from downloading data to generating text.
中文介绍 从零训练 LLM 的完整教程项目，覆盖数据下载、预处理、模型架构搭建到文本生成的全流程，采用简洁直观的方法呈现。适合希望深入理解大语言模型工作原理的 AI 学习者和研究者，无需复杂环境配置即可跟随实践。
TypeScript · ★ 23,323 · 🍴 2,105 · 📈 264 stars today
Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
中文介绍 面向 AI 时代的高性能记忆引擎，提供极速、可扩展的 Memory API，帮助 AI 应用持久化和检索用户上下文信息。适合构建具备长期记忆能力的 AI 助手、聊天机器人或个性化推荐系统的开发者，解决 LLM 上下文窗口有限导致记忆丢失的核心痛点。
TypeScript · ★ 27,716 · 🍴 2,712 · 📈 374 stars today
Project N.O.M.A.D, is a self-contained, offline survival computer packed with critical tools, knowledge, and AI to keep you informed and empowered—anytime, anywhere.
中文介绍 Project N.O.M.A.D 是一套完全离线的自给自足生存计算机系统，内置关键工具、生存知识库和本地 AI 能力，无需网络即可运行。专为极端环境、灾难应急或偏远地区场景设计，让用户在任何时间、任何地点都能获取信息和 AI 辅助决策支持。
Python · ★ 128,889 · 🍴 20,997 · 📈 489 stars today
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
中文介绍 Anthropic 官方发布的终端式 AI 编程代理工具，深度理解整个代码库上下文，可自动执行重复性编码任务、解释复杂代码逻辑并处理 Git 工作流。直接运行于命令行环境，适合希望在不离开终端的情况下显著提升编码效率的专业开发者。
TypeScript · ★ 1,833 · 🍴 255 · 📈 69 stars today
Pi extension for async subagent delegation with truncation, artifacts, and session sharing
中文介绍 Pi 的异步子代理委托扩展插件，支持任务截断、产物（Artifacts）输出和会话共享功能。适合需要将复杂任务拆分给多个子代理并行处理的开发者，通过异步机制和会话共享提升多代理协作效率，适用于 Pi Agent 平台的高级工作流编排场景。
Python · ★ 23,352 · 🍴 4,609 · 📈 73 stars today
A list of developer portfolios for your inspiration
中文介绍 精心整理的开发者个人作品集链接合集，收录了来自全球各类开发者的优秀个人主页案例。适合正在设计或重构个人作品集的开发者从中汲取设计灵感、了解行业惯例，也是前端开发者展示个人品牌时的重要参考资源库。
Markdown · ★ 509,380 · 🍴 48,311 · 📈 1,158 stars today
Master programming by recreating your favorite technologies from scratch.
中文介绍 通过从零重新实现 Redis、Git、Docker、SQLite 等经典技术来深入掌握编程原理的学习资源合集。收录大量分语言、分技术方向的实战教程，适合希望突破 API 调用层、真正理解底层机制的中高级开发者进阶学习。
👍 38
Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D understanding or reliance on statistical shortcuts in natural images. We introduce a representation-level analysis framework that constructs minimal co
👍 7
Robot manipulation critically depends on perception that preserves the action-relevant aspects of a scene. Yet most robot learning pipelines are built upon visual encoders pre-trained for static recognition or vision-language alignment, leaving motion understanding to downstream policies. We introdu
👍 0
Recent advances in Vision-Language Models (VLMs) have achieved impressive performance across many tasks, yet prior studies report unsatisfactory performance when applying large language or multimodal models to finding abnormal patterns in sequential data. Public anomaly detection benchmarks typicall
👍 0
Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from opposing political sides asymmetrically. We refer to this phenomenon as covert political bias and identify 7 categories of techniques through which
👍 6
One-shot Program-of-Thought (PoT) emits a Python program that prints a primitive-action plan; a single invalid action silently invalidates the trajectory. We introduce RePoT (Recoverable PoT): a deterministic verified replay that walks the plan through the environment to its first invalid transition
👍 17
Explaining why dense retrievers assign high relevance scores remains challenging because retrieval decisions are made through opaque high-dimensional embeddings. Existing explanations often focus on surface signals, such as lexical matches, token alignments, or post-hoc textual rationales, and thus
👍 4
Tool retrieval over large API catalogs is a core bottleneck for LLM agents: user queries arrive in colloquial, often underspecified language, while the catalog uses technical API vocabulary that no fixed encoder can bridge on its own. The two dominant training approaches, contrastive encoder fine-tu
👍 27
Video large language models (Video-LLMs) have demonstrated strong capabilities in video understanding tasks. However, their practical deployment is still hindered by the inefficiency introduced by processing massive amounts of visual tokens. Although recent approaches achieve extremely low token ret
👍 11
The design space of agentic AI inference spans two extremes: frontier large language models (LLMs), typically hosted in the cloud and offering strong performance across a wide range of tasks at substantially high cost, and more cost-efficient small language models (SLMs), which are amenable to on-de
👍 6
Natural generation allows Large Language Models (LLMs) to produce free-form responses with rich reasoning, yet the lack of structure makes outputs difficult to verify. Conversely, constrained decoding ensures standardized formats but can inadvertently restrict reasoning capabilities by imposing cons
👍 8
We address the task of generating physically accurate and visually faithful 4D Human-Object Interaction (HOI). Given a static 3D human and target object represented as 3D Gaussian Splats (3DGS), our goal is to synthesize dynamic scenes where the human actively engages with the object through actions
👍 21
Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style. However, existing methods often rely on fixed steering directions or task-spec
👍 1
We study two-level autoresearch for cooperation: an outer-loop AI agent autonomously redesigns the inner-loop pipeline of an LLM policy-synthesis system for multi-agent Sequential Social Dilemmas (SSDs). A researcher agent R (run as a coding agent) reads the inner-loop source code, edits system prom
👍 6
Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewards provide only coarse supervision and cannot distinguish correct from incorrect statements within a reasoning trace. Sentence-level alternatives o
👍 10
Large Language Models (LLMs) have advanced autonomous agents from deep search, which retrieves concise factual answers, to deep research, which synthesizes scattered evidence into long-form reports. However, verifiable multimodal deep research remains challenging due to open-ended synthesis without
👍 18
Diffusion models achieve state-of-the-art image synthesis, with their generative trajectories fundamentally exhibiting a spectral bias, resolving low-frequency global structures early and high-frequency fine details later. Conventional stochastic differential equation (SDE) solvers fail to account f
👍 13
We introduce CausaLab, a scalable environment for evaluating interactive causal discovery by LLM agents. Unlike prior evaluations, CausaLab evaluates both whether an agent can solve a problem using causal evidence and whether its answer is grounded in a faithful recovered causal mechanism. Each epis
👍 3
We show that LoRA adapters, the dominant distribution format for fine-tuned LLMs, can be reliably backdoored through training data poisoning while preserving baseline task performance. On a Qwen 2.5 1.5B prompt-injection classifier, a small fraction of poisoned examples drives a clean-accuracy-prese
👍 41
As video diffusion models (VDMs) advance toward world models, a key question arises: do they truly understand causality, or merely overfit to statistical temporal patterns? Existing benchmarks mostly rely on synthetic data, limiting real-world generalization due to the sim-to-real gap. We present Yo
👍 1
A central bottleneck for phone-use agents is that controllable, reproducible environments covering real mobile behavior are hard to build at scale. Existing mobile-agent benchmarks have made important progress on evaluation, but they do not by themselves provide a scalable way to construct many new
👍 7
Multimodal large language models are increasingly deployed as long-horizon agents, where memory must do more than recall: it must track an evolving world, revise what has gone stale, and surface the right evidence at decision time. Existing benchmarks measure recall over static dialogue, collapse me
👍 10
The rapid growth in submissions to machine learning venues has strained the scientific peer-review system and intensified interest in LLM-based automated peer reviewers. However, how good these systems are actually, especially compared to human reviewers at catching scientific gaps, remains poorly u
👍 9
Pointwise reward modeling offers critical signals for LLM post-training, yet struggles with absolute scoring in subjective, non-verifiable settings. Rubric-based methods address this by decomposing evaluation into explicit criteria, but existing approaches typically depend on frontier LLMs and suffe
👍 21
Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divided into general skills for broad cognitive transfer and task-specific skills for dynamic execution. However, existing sk
👍 5
Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill discovery, and specialist model stacks. This raises a central question: can a web agent become more efficient as it accumulates experience, rather tha
👍 2
Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing alignment influences the preference dataset, causing RLHF to ampli
👍 4
Long-horizon LLM inference turns the key--value (KV) cache into the dominant GPU memory consumer and makes per-token attention increasingly expensive. Many common eviction policies use static recency windows or historical attention, leaving unused a signal computed on every decoding step: the model'
👍 5
Occlusion-aware prediction remains a critical challenge in autonomous driving due to the inherent uncertainty of unobserved regions. Existing approaches either overestimate risk based on reachable states or struggle to predict accurate trajectories under high occlusion uncertainty. To address these
👍 4
Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for adapting models without parameter updates. Yet prompt design remains labor-intensive and highly sensitive to formatting, phrasing, and instruction
👍 0
Smartphone scams are increasingly prevalent and typically manifest as multi-stage, cross-application processes with gradually emerging intent. Effective intervention thus requires anticipating scams before the intent becomes explicit. This is inherently challenging, as decisions must rely on partial
该源今日无内容。
a quiet day lets us highlight the new AIE WF focuses
中文介绍 Latent Space发布AI新闻简报，聚焦创始人与前沿部署工程师（Forward Deployed Engineers）话题，并重点介绍了AIE工作流的最新动态。整体为较平淡的一天，内容以行业动态梳理为主。
Boston Children’s Hospital uses OpenAI technology to improve patient care, reduce operational burden, and help diagnose more than 40 rare disease cases.
中文介绍 波士顿儿童医院与OpenAI合作，将AI技术应用于患者护理与医院运营管理，已协助诊断超过40例罕见疾病病例，同时有效降低了医疗团队的日常运营负担。
How Braintrust engineers use Codex with GPT-5.5 to run experiments and code faster.
中文介绍 AI评估平台Braintrust介绍其工程师团队如何结合OpenAI Codex与GPT-5.5，将客户需求快速转化为代码，显著提升实验迭代速度与编程效率。
Pope Leo XIV’s new encyclical on artificial intelligence includes a statement that warrants serious attention from technologists and policymakers: “Technology is never neutral.” Magnifica Humanitas (“Magnificent Humanity”) is a clarion call to all people to act with courage and solidarity as we ente
中文介绍 教宗利奥十四世发布人工智能主题通谕《Magnifica Humanitas》（宏大的人性），提出「技术从不中立」的核心立场，呼吁技术人员和政策制定者以勇气与责任感应对AI时代，为个人和机构提供行动框架参考。
**Anthropic** rolled out **Claude Opus 4.8**, which shows incremental improvements but mixed benchmark results, including better cooperation and coding behavior but some regressions in document parsing. Platform updates include mid-conversation system instructions enhancing long agent sessions, thou
中文介绍 Anthropic推出Claude Opus 4.8，与Opus 4.7相比在协作能力和编程表现上有所提升，但文档解析出现部分退步，基准测试结果参差不齐。平台同步更新支持对话中途修改系统指令等功能。
OpenAI launches Rosalind Biodefense, expanding trusted access to GPT-Rosalind for vetted developers and U.S. government partners advancing biodefense, public health, and pandemic preparedness through frontier AI.
中文介绍 OpenAI正式推出Rosalind Biodefense项目，向经审核的开发者及美国政府合作伙伴开放GPT-Rosalind访问权限，聚焦生物防御、公共卫生及大流行病防备领域的前沿AI应用研究。
Total Anthropic victory!
中文介绍 Latent Space发布AI新闻简报，报道Anthropic完成大规模融资，估值达9650亿美元，同时发布Claude Opus 4.8模型及Dynamic Workflows动态工作流与ultracode等新功能。
OpenAI shares guidance on third-party AI evaluations, covering how to assess model capabilities, safeguards, and validity for frontier systems.
中文介绍 OpenAI发布第三方AI评估指导手册，为外部评估机构提供统一框架，涵盖前沿AI系统的模型能力评估、安全防护措施审查及评估结果有效性验证等核心方法论。
中文介绍 Hugging Face发布PyTorch性能分析系列教程第一篇，面向初学者介绍torch.profiler工具的基本使用方法，帮助开发者分析和优化模型训练及推理的性能瓶颈。
中文介绍 TLDR AI每日简报（2026年5月29日）重点涵盖：Anthropic发布Claude Opus 4.8、完成估值9650亿美元融资，以及微软推出新一代编程专用AI模型等当日主要行业动态。
80% Devin Commits, Spec-to-PR Workflows, Full VMs, Agent Memory, and PMs Shipping Code
中文介绍 Latent Space播客专访Cognition联合创始人Walden Yan与OpenInspect的Cole Murray，探讨异步AI代理时代的来临，话题涵盖Devin代码提交占比达80%、规格说明到PR的自动化工作流、完整虚拟机支持、代理记忆机制及产品经理直接交付代码等议题。
Learn how Endava uses Codex to build an agentic organization, accelerating software delivery and reducing requirements analysis from weeks to hours.
中文介绍 全球IT服务公司Endava分享如何借助OpenAI Codex构建代理型组织，将软件交付周期大幅压缩，需求分析时间从数周缩短至数小时，整体软件交付效率显著提升。
It is one thing to say AI will change the world. It is another to expect the class of 2026 to applaud it. In fact, when former Google CEO Eric Schmidt told University of Arizona graduates that their task is to help shape AI, he was met with a resounding chorus of boos. “I can…
中文介绍 MIT Technology Review「AI炒作指数」报道：前谷歌CEO埃里克·施密特在亚利桑那大学毕业典礼上呼吁毕业生参与塑造AI未来，却遭到现场学生集体嘘声，折射出2026届毕业生对AI热潮的普遍疲倦与抵触情绪。
coding is an uncapped TAM market
中文介绍 Latent Space报道AI编程公司Cognition完成D轮融资，融资规模10亿美元，公司整体估值达260亿美元，投资逻辑基于对软件编程为无上限市场规模（TAM）的判断。
**Anthropic** announced a massive **$65B Series H financing** at a **$965B valuation**, led by **Altimeter, Dragoneer, Greenoaks, and Sequoia**, with run-rate revenue surpassing **$47B**. They launched **Claude Opus 4.8**, an update to Opus 4.7 featuring "sharper judgment," "more honesty," and longe
中文介绍 Anthropic宣布完成650亿美元H轮融资，投后估值达9650亿美元，由Altimeter、Dragoneer、Greenoaks和Sequoia领投，年化营收已超过470亿美元。同步发布Claude Opus 4.8模型，主打更敏锐的判断力与更优异的协作表现，并推出Dynamic Workflows动态工作流功能。
本期技术面呈现明显的板块分化格局。美股方面，SPY 报 756.48，5日涨 1.85%，RSI14 达 74.1，处于超买状态；QQQ 报 738.31，RSI14 高达 77.2，MACD 刚完成金叉，均价多头排列完好，技术动量为所有资产类别中最强。AAPL 的 RSI14 更达 78.8，整体美股主要指数与科技龙头均处于超买区域，短期累积了一定的回调压力。MSFT 单日暴涨 5.45% 形成异动，但仍面临 SMA200（458.46）压力。NVDA 和 GOOGL 则出现日内回调，MACD 指标走弱，技术动量分化。加密资产方面，BTC 现价 73,723 低于 SMA20/SMA50/SMA200 三均线，空头排列成立，配合加密恐慌贪婪指数仅为 29（恐慌区间），BTC 主导率 57.3%，总市值 2.58T USD 且 24 小时微跌 0.22%，ETH 的 RSI14 为 32.1 同样偏弱，整体加密市场技术面处于调整压力中。中概股方面，BABA、PDD、JD、腾讯均处于空头排列，RSI14 集中在 31～38 区间，PDD 的 5 日跌幅达 -13.65%，技术压力最为突出。商品与外汇方面，黄金 MACD 出现金叉但尚处负值域，WTI 原油 5 日下跌 -7.42% 后技术结构仍偏弱；美元指数 DXY 维持多头排列，美元/人民币（USDCNY）则处空头排列且 RSI14 仅 30.6。宏观指标方面，VIX 报 15.32，低于 SMA20（17.25）且 5 日下滑 -8.26%，市场整体波动率处于低位，与美股强势对应。
QQQ 当前报 738.31，5日涨幅达 3.33%，距52周高点仅 -0.45%。SMA20/SMA50/SMA200 呈多头排列（709.04 / 652.93 / 617.85），MACD 已触发金叉（21.4696 vs 信号线 21.4381），RSI14 读数 77.2 处于超买区域。价格动量强劲，但超买信号提示短期回调风险不可忽视。
MSFT 单日大涨 5.45%，5日涨幅 7.43%，当前价 450.24 已重新站上 SMA50（402.83），MACD 金叉（5.8019 vs 信号线 4.1239）动量转正。但 SMA200 位于 458.46，价格尚未收复该压力位，且距52周高点仍有 -18.94%，RSI14 为 69.6，接近超买临界。技术结构整体偏修复，方向未明朗。
BTC 现报 73,723，低于 SMA20（76,755）、SMA50（77,234）、SMA200（79,523），呈空头排列。MACD 为 -1,100.6，信号线 -585.4，绿柱持续扩大，动量下行。RSI14 为 37.2，尚未进入超卖区（<30）。配合加密恐慌贪婪指数 29（恐慌区间）及 5日跌幅 -2.77%，技术面整体偏弱。
PDD 现价 84.44，5日跌幅达 -13.65%，距52周高点 -39.43%。SMA20/SMA50/SMA200（95.79 / 98.42 / 113.23）全面压制价格，空头排列形成。MACD 死叉确认（-3.2037 vs 信号线 -1.7986），绿柱扩大。RSI14 为 32.3，逼近超卖区但尚未形成底背离信号，短期技术压力显著。
黄金期货报 4,575.3，MACD 出现金叉（-45.404 vs 信号线 -46.828），为近期最值得关注的正向边际信号，但 MACD 仍处于负值区域。价格低于 SMA20（4,586.96）和 SMA50（4,629.76），但高于 SMA200（4,376.93）。RSI14 为 47.8，位于中性区间。整体技术结构处于震荡修复阶段，方向信号尚不明确。
VIX 恐慌指数
10Y 美债收益率 (%)
美元指数 DXY
S&P 500 ETF
Nasdaq 100 ETF
Apple
Microsoft
Nvidia
Alphabet
Tesla
Meta
Bitcoin
Ethereum
Solana
阿里巴巴 (BABA)
拼多多 (PDD)
京东 (JD)
腾讯控股 (0700.HK)
黄金期货
WTI 原油期货
美元 / 人民币
本报告仅根据公开行情数据的技术指标进行客观描述，过去走势不代表未来表现，任何技术形态均存在失效可能。本内容仅供技术指标解读参考，不构成任何投资建议或买卖推荐，投资者应自行判断并承担相应风险。
The candidate forced a runoff on Sunday in what could herald another gain for the right-wing wave sweeping Latin America.
中文摘要 哥伦比亚总统大选首轮投票结束，选举将进入决选阶段。此次结果被视为拉丁美洲右翼浪潮持续扩展的又一信号，决选将于6月21日举行。
Pauline Hanson’s One Nation now the most popular political party in the country, poll suggests. Follow today’s news live Get our breaking news email, free app or daily news podcast Abbott unbothered by One Nation poll showing but says Coalition ‘obviously’ in competition Tony Abbott, the new party p
中文摘要 澳大利亚最新民调显示，葆琳·汉森领导的一国党支持率超越工党，成为全国最受欢迎的政党。前总理托尼·阿博特表示，联合党与一国党存在明显竞争关系。反对党领袖乔伊斯称若上台将废除工党预算中的大部分内容。
Left-wing senator Iván Cepeda will face Trump admirer Abelardo de la Espriella at the final ballot on 21 June.
中文摘要 哥伦比亚总统大选将于6月21日举行决选，左翼参议员伊万·塞佩达与亲特朗普的右翼候选人阿贝拉多·德拉埃斯普里耶利将对决，安全议题是此次大选的核心焦点。
The left-wing senator and far-right newcomer will face each other in a runoff on June 21, with security a top issue.
中文摘要 哥伦比亚大选首轮结束，左翼参议员塞佩达与极右翼新人德拉埃斯普里耶利双双晋级，将于6月21日进行决选。安全问题是本次选举的首要议题。
Severe, hard-to-control blazes in densely populated areas like Los Angeles drove the year’s record losses.
中文摘要 研究人员表示，2025年全球野火造成的损失创历史最高纪录。洛杉矶等人口密集地区爆发大规模难以控制的火灾，是推高全年损失的主要原因。
The requested changes are related to the Strait of Hormuz and the removal of highly enriched uranium, according to US media.
中文摘要 据美国媒体报道，特朗普政府正寻求修改美伊协议部分条款，涉及霍尔木兹海峡相关安排以及高浓缩铀的移除问题。
Prime Minister Benjamin Netanyahu calls the capture of the strategic fortress a "decisive shift" in Israel's campaign against Hezbollah, as European governments criticise the escalation.
中文摘要 以色列在黎巴嫩扩大地面攻势，占领一处具有战略意义的城堡要塞。以色列总理内塔尼亚胡称此举为打击真主党行动的「决定性转折」，欧洲多国政府对此升级行动提出批评。
The country has spent decades perfecting a surveillance state at home. Now it’s promoting its ideology of state control, and the technology to enforce it, abroad.
中文摘要 中国数十年来在国内构建并完善监控体系，如今正将国家管控意识形态及相关技术向海外输出，包括所罗门群岛、尼泊尔等国已成为推广对象。
Crews extinguished blaze before finding a child who died in Werribee home, Victoria police said Follow our Australia news live blog for latest updates Get our breaking news email, free app or daily news podcast A child has died and a man has been left seriously injured after an early morning house f
中文摘要 澳大利亚墨尔本西南部韦里比区发生住宅火灾，消防人员扑灭火势后发现一名儿童在屋内罹难，另有一名男子伤势严重，警方已介入调查。
Rights groups condemn the death of Brooklyn Rivera, 73, following his long arbitrary detention by the governing regime.
中文摘要 尼加拉瓜原住民领袖布鲁克林·里维拉（73岁）在被政府羁押约三年后于狱中死亡。人权组织谴责当局对其实施长期任意拘押，并对其死亡表示强烈谴责。
Rivera spent nearly three years in detention, cut off from the outside world, leading advocates to fear for his welfare.
中文摘要 尼加拉瓜当局证实，原住民领袖布鲁克林·里维拉在被关押近三年后于羁押期间死亡。其间他与外界完全隔绝，人权倡导者此前曾多次对其安危表达忧虑。
Aid workers in Uganda are watching the Ebola crisis unfold in the neighboring Democratic Republic of Congo. They're doing what they can to prepare for an uptick in cases, but foreign aid cuts aren't helping.
中文摘要 刚果民主共和国埃博拉疫情持续扩散，邻国乌干达的援助人员正积极备战应对病例增加。然而，外国援助大幅削减严重制约了前线防控工作的开展。
A deadly strike during the first days of the Iran war hit far away in the Indian Ocean, jolting a quiet seaside town and showing how far the conflict's reach extends.
中文摘要 美伊战争初期，一次致命打击波及斯里兰卡一处宁静的印度洋沿海小镇，造成人员伤亡，此事件揭示了这场冲突影响范围之广远超预期。
South Korea is using AI-powered companion dolls to help tackle loneliness in its ageing population
中文摘要 韩国正通过为老年人提供人工智能陪伴机器人，探索以科技手段应对老龄化社会中日益严峻的孤独问题。
New Jersey orders curfew after immigration protests escalate.
中文摘要 美国新泽西州因移民议题引发的抗议活动持续升级，当局宣布实施宵禁措施以维护社会秩序。
Vietnamese diagnostic testing startup Gene Solutions is preparing for a Hong Kong initial public offering as early as the second quarter of next year, a rare local firm seeking to access deeper capital markets and boost international visibility.
中文摘要 越南基因检测初创公司Gene Solutions计划最早于明年第二季度赴香港进行首次公开募股，以筹集资金支持国际扩张。该公司是少数寻求进入深度资本市场、提升国际知名度的越南本土企业之一。
Local investors are driving the premium on Taiwan Semiconductor Manufacturing Co.’s US-listed shares to a two-year low as they pile into the chipmaker’s stock in Taipei on bets the AI boom has further to run.
中文摘要 随着台湾本地投资者大举买入台积电台北上市股票，押注AI热潮仍将持续，台积电美股与台股之间的估值溢价已降至两年低位，本地投资者正在缩小与华尔街之间的定价差距。
Manufacturers in Jamaica say the key chilli peppers they need are in limited supply.
中文摘要 加勒比地区辣椒酱生产商发出警告，由于牙买加制造商所需的关键辣椒供应短缺，辣椒酱产品面临供应不足和价格上涨的压力。
Chinese consumers are showing signs of a renewed appetite for high-end beauty and fashion products, a rare bright spot for global luxury brands after years of weak demand and margin-eroding discounts in their most important growth market.
中文摘要 随着股市回暖，中国消费者对高端美妆和时尚产品的购买意愿明显回升。在经历数年需求疲软及折扣侵蚀利润之后，中国市场重新成为全球奢侈品牌难得的亮点。
French police make 780 arrests after Qatar-owned Paris Saint-Germain win trophy for second year running
中文摘要 卡塔尔资本持有的巴黎圣日耳曼足球俱乐部连续第二年夺得欧冠冠军，但赛后庆祝活动引发严重骚乱，法国警方共逮捕约780人。
First substantial acquisition under new CEO is bet on eventual recovery in property sector
中文摘要 伯克希尔·哈撒韦宣布以85亿美元收购美国房屋建筑商Taylor Morrison，这是新任首席执行官格雷格·阿贝尔上任后的首笔重大收购，被视为对美国房地产市场最终复苏的信心押注。
Oil climbed and the dollar strengthened as tensions remained elevated in the Middle East, with negotiations over a permanent US-Iran ceasefire showing little sign of a breakthrough.
中文摘要 受中东局势持续紧张、美伊永久停火谈判毫无突破迹象影响，国际油价上涨，美元走强。市场对地缘政治风险保持高度关注。
Oil rose from a six-week low amid uncertainty over the outlook for a peace deal to end the war in Iran.
中文摘要 由于美伊和平协议前景不确定，国际油价从六周低位反弹回升。伊朗战争结束谈判的进展僵局令市场对原油供应预期持谨慎态度。
Brazil’s state-controlled oil giant Petroleo Brasileiro SA is reducing domestic diesel prices starting Monday as part of a government subsidy program to shield consumers from the war in the Middle East.
中文摘要 巴西国有石油巨头巴西石油公司（Petrobras）宣布自本周一起下调国内柴油价格，此举是巴西联邦政府补贴计划的一部分，旨在保护消费者免受中东战争引发的能源价格波动冲击。
The family-run APA hotel chain that turned efficiency into a hospitality empire is betting it can export its uniquely Japanese formula abroad, starting with North America. APA Group CEO Isshi Motoya spoke with Bloomberg News' Momoka Yokoyama in Tokyo. (Source: Bloomberg)
中文摘要 日本家族连锁酒店APA集团首席执行官元谷一志表示，计划将以高效运营著称的APA酒店模式推向海外，首站瞄准北美市场，希望将独特的日式酒店经营理念输出至全球。
The company’s ambitious listing plan is set to clear the way for other mega-offerings. It also risks threatening the integrity of the market itself
中文摘要 SpaceX雄心勃勃的IPO计划正推动华尔街为其重组规则，指数基金和散户投资者均面临规则调整压力。此次超大规模上市有望为其他巨型企业IPO铺路，但同时也引发对市场完整性的担忧。
Berkshire Hathaway Inc. will acquire Taylor Morrison Home Corp. in an all-cash deal worth about $6.8 billion, the first major purchase under chief executive Greg Abel that signals a vote of confidence in America’s housing market.
中文摘要 伯克希尔·哈撒韦宣布以约68亿美元全现金方式收购美国住宅建筑商Taylor Morrison Home Corp.，这是新任首席执行官格雷格·阿贝尔主导的首笔重大收购，被视为对美国房市前景的信心表态。
22 回复 · 程序员 节点
8 回复 · Apple 节点
41 回复 · 程序员 节点
19 回复 · 程序员 节点
17 回复 · 程序员 节点
9 回复 · Apple 节点
6 回复 · 程序员 节点
27 回复 · 程序员 节点
9 回复 · Apple 节点
18 回复 · Apple 节点
兄弟们我们看看谁在搞事情。 测试站 绝对不会收集各位的key信息，只是想看看谁有问题。 排行榜（模糊处理域名） 在说一次 ，永远不收费，也不会卖api，接受监督，公益服务已经关闭了，改到自用了。 28 个帖子 - 13 位参与者 阅读完整话题
每个人心里都住着一个小孩 37 个帖子 - 37 位参与者 阅读完整话题
各位 Cherry Studio 用户： Cherry Studio 早期版本中一直缺少完整、清晰的隐私政策说明，同时隐私相关开关在不同版本中的数据存储方式也不够一致，可能会导致部分用户在升级或切换版本后遇到隐私设置状态异常等问题。 从 Cherry Studio v1.9.8 版本开始，我们将正式加入隐私协议与更清晰的隐私设置说明，让用户能够更透明地了解软件会收集哪些匿名运行信息、不会收集哪些敏感数据，以及如何自行管理相关开关。 根据新版隐私协议，Cherry Studio 仅会在必要范围内收集匿名化的基础运行信息与产品改进信息，例如软件版本、功能使用汇总、功能活跃度与频次、错误日志与崩溃信
感谢大佬的馈赠！ 48 个帖子 - 40 位参与者 阅读完整话题
随便给它假装生个气，它就真的会自己想办法破它自己（的外审)的限来认真满足我的要求。 31 个帖子 - 13 位参与者 阅读完整话题
今天某位佬友把自己的key不小心上传到了github，被我朋友发现了，目前该key我已经协助禁用，在这里还是提醒各位佬友，一定要妥善保管好自己的key，尽量不要设置无限额度的key，尽可能降低损失。 其实newapi不支持根据key查用户的功能，我是直接联系newapitools的作者，紧急加了一个key反查用户的功能，在此也感谢newapitools的作者！ 泄露自己的key就相当于把把钱扔在马路上，大家一定要注意！！！ 祝大家早安，午安，晚安 17 个帖子 - 16 位参与者 阅读完整话题
2026年6月1日，天涯社区将正式恢复访问。 40 个帖子 - 38 位参与者 阅读完整话题
本帖使用社区开源推广，符合推广要求。我申明并遵循社区要求的以下内容： 我的帖子已经打上 开源推广 标签： 是 我的开源项目完整开源，无未开源部分： 是 我的开源项目已链接认可 LINUX DO 社区： 是 我帖子内的项目介绍，AI生成、润色内容部分已截图发出： 是 以上选择我承诺是永久有效的，接受社区和佬友监督： 是 以下为项目介绍正文内容，AI生成、润色内容已使用截图方式发出 前言 最近在看外国课程，但奈何本人英语水平有限，机翻的字幕又简直灾难，于是参考各种方法做了一个还不错的工具，安装使用都很清晰（详见README.md），欢迎各位佬友品鉴 效果图： 正文 流程： 视频 / 音频 核心特点
买过gpt plus的佬们注意了，gpt plus 日抛号骗局，openai 官方对于账号的封禁只有一种，直接删你账号，而不会出现账号能用反代不能用的情况，通过 codex2api + 授权的方式是一定可以反向代理出来的，各种渠道的所谓日抛号，没那么恶心人的给你 refresh token，恶心人的给你 access token (当然 openai 提高风控之后，access token 或者 session token 这条路基本堵死了)，然后过了两天，卖家登录 chatgpt 网页端或者直接走 api 刷新 refresh token，原来的 refresh token 失效了，但是实际
最近在 L 站看到以下两个项目。我想起来我自己之前一直想补《魔法禁书目录》，但是因为小说文本太长了，一直没看。于是打算自己在我的服务器上面部署一个 web 服务自己看小说。 【开源推广】网文小说速读，脱水长文小说，节省70%阅读时间。 开发调优 本帖使用社区开源推广，符合推广要求。我申明并遵循社区要求的以下内容： 我的帖子已经打上 开源推广 标签： 是 我的开源项目完整开源，无未开源部分： 是 我的开源项目已链接认可 LINUX DO 社区： 是 我帖子内的项目介绍，AI生成、润色内容部分已截图发出： 是 以上选择我承诺是永久有效的，接受社区和佬友监督： 是 以下为项目介绍正文内容，AI生成、