WeWorkBuddy

Home / Browse

All stories

Browse every indexed public story, including items outside the main categories.

7967 public stories

Product Hunt ·

NEXUPIRA

AI teammates that hand back finished work

Hacker News ·

Show HN: Privato - smart, scoped and temporary data access for personal agents

Hi HN! Sharing our latest open-source project: Privato Agents now get access to our email, texts, calendar, files, everything. They can read whatever they like, whenever they like. We sacrifice personal data privacy for max productivity. But we no longer have to. Privato gives AI agents a scoped, temporary pass to ONLY the data it needs to answer a question. If you ask "When does my flight to Tokyo leave?", the agent accesses your airline emails about that trip for 10 minutes, nothing

V2EX ·

[推广] 给室友做了个生日整蛊视频，顺手做成了一个网站

先说明，这是我自己做的站，所以发在推广节点。 上个月室友过 30 岁生日，群里几个人商量送点什么有意思的。有人提议做个视频，我就翻出大学时我们三个在宿舍楼下的合照，想让他们俩"上台"来一段说唱对决。 结果试了一圈工具，要么脸像贴纸一样糊在别人身上，要么嘴型和节拍完全对不上，看着很出戏。折腾了几个晚上，干脆自己做了一个，就是 Rapvora 。 生日那天视频一放，全场笑疯，寿星本人看了三遍。后来群里好几个朋友来找我要，我就把它整理成了网站。 它能做什么 上传 1~3 张照片，对应单人、双人对战、三人组合 可以一键套用热门说唱模板，也可以选生日、损友、炫技、品牌宣传等场景 自带卡点音轨，嘴型跟着节奏走，不用自己剪辑配乐 支持竖屏 9:16 、横屏 16:9 、方形 1:1 ，最高可选 4K 下载没有水印，可以直接发抖音、Reels 、Shorts 手机扫码就能上传照片，也能扫码下载成品 注册送免费积分，生成失败会自动退还 几个小建议 尽量用光线好的正脸照，别戴墨镜、口罩 做双人对战时，两个人的照片风格接近一点效果更好 给朋友做生日或整蛊视频的话，场景直接选对应的就行 做这个的初衷就是好玩，

V2EX ·

[分享创造] 做了一个 Chrome 插件:ReadTube，通过遮罩视频减少学习干扰

在 Youtube 上筛选英文磨耳朵，开发了一款遮蔽视频的小插件 ReadTube 致力于为你打造一个“无干扰、可交互、高效率”的沉浸式影音学习环境。 ✨ 核心功能亮点 减少干扰，专注模式自动隐藏右侧推荐视频 一键开启极简专注空间，结合悬浮面板友好控制 适合用来精读外语视频、专业网课及技术讲座。 不收集任何个人隐私数据。 🎯 适用人群 语言学习者：配合双语字幕和沉浸视图，摆脱弹幕和推荐干扰，专注听力与口语训练。 开发者与终身学习者：高效观看长视频教程、技术分享与学术讲座，把视频网站变成你的个人数字自习室。 ReadTube 谷歌插件下载

V2EX ·

[问与答] 退休后还打算回农村老家养老吗

经常梦到小时候村里的场景，那个小山村已经融入了我的灵魂 梦想退休后，回到小时候长大的村里，渡过余生 但，又有不少现实问题，令人望而却步 焦虑的灵魂无处安放

V2EX ·

[分享创造] 做了个查询广告案例的 MCP

我一直在广告行业，每次写提案或者策划都需要搜索各种案例，创意枯竭的时候也想看看别人有什么好想法（没错，就是抄作业）。 以前用 Google 搜索，搜出来一堆内容得自己分辨，垂直网站的搜索功能又比较弱。 所以做了一个广告行业的案例库，并提供 MCP 查询功能。 先用爬虫抓了来自各个广告行业案例垂直网站的大概 16 万条内容，烧了十几亿 GPT token 全部分析了一遍，包括匹配重复案例、抽取品牌、创意机制等要素。 最后整理出来 8 万多个案例，19 万个创意机制，覆盖 2 万多品牌。 平时自己也用，感觉查询效果还行，不过实际反馈内容也取决于用户端的 AI 客户端是什么，个人体感 Codex 可能更好一些。 https://admuse.cn/ 注册可以免费查询 3 次，愿意帮忙测试的朋友可以给我注册手机号，我给你手动加。 如果有啥用着不方便的或者不满意的，欢迎反馈，非常感谢🙏

V2EX ·

[推广] 《我享云》机场代理｜低至一两元体验专线线路｜两种套餐自由选择

《我享云》机场代理｜一两块钱也能用上专线 不想花高价，也想体验专线线路？套餐选择不必盲目追求高等级，适合自己的才是最划算的。 一、线路与性价比 提供专线节点等线路资源，具体以当前实际上线情况为准。目前受网络阻断影响，已下线直连相关节点，保留专线节点。 所有级别套餐节点资源一致，套餐倍率不同。 根据自己的使用需求选择合适的倍率，让有限的预算也能用上专线。 二、两种套餐，灵活选择 周期性套餐（订阅制）： 适合长期稳定使用的用户。 无时间限制套餐（买断制）： 不想定期续费，可以选择这种模式。 不必为用不上的配置买单，按需选择更划算。 三、11 月优惠活动 套餐类型 折扣 优惠码 周期性套餐 6.8 折 eZSdiffE 无时间限制套餐 7 折 disNPffz 活动时间： 2026/11/01 — 2026/11/15 👉 套餐详情及优惠领取： https://m.vxcloud.cfd/coupon.html 小预算也能用专线，倍率灵活选，订阅或买断随你选。

Product Hunt ·

Stitch.ai

Your AI workspace for mail, calendar, notes, tasks and more

V2EX ·

[程序员] 一个用于前端 wasm 的自创密码学算法，欢迎破解~

具体功能：在线网页测量用户的 CPU 主频，并挑战排行榜。 （查看演示） 要实现这个功能，最简单的办法就是用 js/wasm 跑一段消耗 CPU 周期比较稳定的程序，测量起始和结束的时间差，然后上报到服务端。 但这有个严重的问题：时间是在前端测量的，用户可以伪造。即便对程序加密混淆，现在也不难破解。所以必须用一些密码学机制，从原理上堵住这个漏洞。例如使用 VDF 函数进行计算，这样客户端必须老老实实执行每一步才能得出正确的结果。 但这还有另一个问题：这个算法是跑在网页里的，因此必须能被 JIT 充分优化，接近甚至达到原生程序的性能才行，否则作弊者可以用原生程序代替网页版。要符合这个条件，稍复杂一点的算法可能就不满足了。例如有些 VDF 函数基于大数运算，在原生程序里可充分利用 CPU 专用指令，比 wasm 版本快几倍。 因此这个算法必须足够简单，尽可能规避各种损耗。目前这个版本非常简单，只有纯粹的寄存器运算，在网页里和本地 C 程序几乎一样快；同时为了确保强度，模仿密码学中的 ARX (Add–Rotate–Xor) 运算，并且把加法换成了乘法，因为乘法的扩散效果更好，并且硬件实现也

Product Hunt ·

Corvo

A mailbox that tidies itself as mail arrives

Simon Willison ·

I discovered a sound that leaks your exact location (and it's everywhere) - YouTube

I discovered a sound that leaks your exact location (and it's everywhere) - YouTube Genius piece of OSINT by Colsto, who demonstrates how you can take almost imperceptible background noise of planes from a video soundtrack, figure out their Doppler curves, then cross reference them against ADS-B data to find the exact location of the video based on their speed, distance, and gaps between different flights. Via Lobste.rs Tags: privacy , youtube

Simon Willison ·

October sponsors-only newsletter

I sent out the October edition of my sponsors-only monthly newsletter . If you are a sponsor (or start a sponsorship now) you can access it here . This month: The October inflection point for vibe game development The vulnerability apocalypse gets hot LLM releases API credits for $100+/month subscriptions What I'm using right now My software releases My September newsletter can now be seen here , as a preview of what you'll get. Pay $10/month to stay a month ahead of the free copy! Tags: newslet

arXiv ·

A Generalized Sparse Fuzzy Clustering Framework with Automated Cluster Cardinality Estimation Ability

arXiv:2611.00159v1 Announce Type: new Abstract: Fuzzy clustering provides a robust framework for handling ambiguous and overlapping data boundaries, yet its traditional formulation generates entirely dense membership assignments that limit noise resilience and prevent estimating the true number of clusters, when it is unknown. To address these limitations, we introduce in this paper the Generalized Sparse Fuzzy Clustering (GSFC) framework, which incorporates a continuous sparsity penalty into th

arXiv ·

Learning to bid and bundle: a posterior-sampling agent for online retail

arXiv:2611.00165v1 Announce Type: new Abstract: An online retailer launching a perishable product bids for sponsored-search clicks, discounts a bundle with an always-stocked staple and displays its remaining stock, which raises willingness to pay. It knows neither how clicks respond to its bid nor how strong and dispersed its market is, and learns both over repeated seasons from data its own decisions censor: a zero bid reveals nothing about paid clicks, and choices follow only clicks. We design

arXiv ·

Early Stopping in Large Reasoning Models: A Survey and Empirical Audit of Efficiency and Reliability

arXiv:2611.00166v1 Announce Type: new Abstract: Large reasoning models can improve accuracy by generating longer reasoning traces, but some of this computation may be unnecessary. Early-stopping methods aim to stop once enough reasoning is available to answer. Evaluating these methods requires accounting for the cost of deciding when to stop and the reliability of the resulting answer. We evaluate different methods across five reasoning models on mathematical and scientific reasoning, code gener

arXiv ·

PatchScout: Thematic Web Data Collection via Information Foraging

arXiv:2611.00169v1 Announce Type: new Abstract: Researchers often need web corpora that are not answers to a single query, but reusable collections of documents spanning many decentralized sources. We refer to this problem as thematic web data collection: assembling semantically relevant documents that share a common theme but are scattered across heterogeneous and structurally disconnected regions of the web. Existing approaches, including traversal-based methods and LLM-driven web agents, are

arXiv ·

Reimagining Text-to-SQL: A Survey of Large Language Model Architectures and Strategies

arXiv:2611.00171v1 Announce Type: new Abstract: Text-to-SQL systems translate natural language questions into executable SQL queries, democratizing access to relational data. Early approaches relied on handcrafted rules and template matching, while subsequent neural methods introduced encoder-decoder architectures, schema linking, and constrained decoding to handle increasingly complex queries. The emergence of large language models (LLMs), exemplified by systems such as ReFoRCE, Agentar-Scale-S