WeWorkBuddy

首页 / 浏览

全部内容

浏览全部已收录的公开内容,包括尚未归入主分类的条目。

18978 条公开内容

V2EX ·

[分享创造] libcr 项目组发布的跨平台开源远程桌面应用 crDesk

支持 Windows 、Linux 和 macOS 。C++实现的,底层基于 Chromium + GPU + WebRTC ,设备支持设备的硬件视频加速 支持屏幕共享、远程键鼠控制、文本与图片剪贴板同步,以及系统声音和麦克风共享;文件传输支持队列、进度显示和完整性校验 提供局域网自动发现、多标签页与独立窗口,并通过连接密钥、临时访问令牌、可信设备配对和独立权限管理控制访问。 针对不同系统,还提供 Windows 服务、Linux Portal/EIS 与 KMS/UHID 集成,以及 macOS 登录后自动共享,可按平台配置锁屏访问或无人值守。适合局域网或 VPN 环境下的远程操作, https://github.com/wuruxu/crDesk

V2EX ·

[推广] [LinkAGI] Codex 配置包已更新, 0.15 倍率起,进群领 3 元试用

LinkAGI 是我在运营的 API 中转站。最近把 Codex 的接入配置整理成了一个小包,已经装好 Codex CLI 的朋友,可以直接拿去配。 里面有独立的 profile 和 Windows 、macOS / Linux 的使用说明,不用覆盖原来的默认配置。适用于 Codex CLI 0.134.0 及以上,包里不带 Key ,填自己的就行。 下载配置包 · 先看接入教程 · GitHub 发布页 Codex 专用组目前是 0.15 倍率 ,按量计费。 模型和价格 可以直接看。 想试的朋友,注册后进群领 3 元体验额度 ,不用先充值。拿自己手头的任务试一试,看看速度、效果和实际花费是否合适。配置或调用遇到问题,也可以在群里找我。 官网: api.linktoagi.com 注册试用 QQ 群: 342205412 · 点击加群

V2EX ·

[分享创造] 固件的开发 可以用 ai 完成吗

如果一个硬件开发项目要换芯片 是不是用 ai 就可以搭建芯片底层固件代码 然后应用层可以自己开发了 假如程序员是一个传统的 windows 软件开发

V2EX ·

[推广] 🎃 万圣节不搞套路: Proxy001 注册送 1GB 真实住宅 IP,速来,手慢无

🎁直接放码,每个 = 1GB 动态住宅流量,注册后控制台 CDK 兑换: 11KNZWIKSTZHZLS4JG6EHGE6Z438DWY4 2Q2SSBOCBWLHWHSXL6V2J94RKPG6B27I EAWIRKISBKZQ50HDF8V01D9W8QDJ6B2O C5M8X3KZ4SFHUMPWYBNYE79UBSULR8Q3 ⚠️⚠️每人限兑换 1 个,恶意兑换多个,账号会被封禁 🎁🎁没抢到的朋友,别着急,按照以下步骤,后台赠送领取 1.添加 TG 号: https://t.me/ipproxy588 2.发送客服:注册邮箱账号+额外赠送 1GB 测试,后台赠送测试 领完回帖扣 1 ,再补一批 🧛 ━━━━━━━━━━━━━ 🟢 动态住宅:$0.55/GB 起 1 亿+ 真实家庭 IP ,200+ 国家,城市级定位 99.8% 连接率,响应 < 0.3s ,HTTP/SOCKS5 全支持 🟡 静态 ISP:$2.9/IP/月 起(美区) 独享固定 IP ,不限流量不限并发,养号跑号长期稳 🔴 无限套餐:$35/天 起 100Gbps+ 带宽,YouTube

V2EX ·

[程序员] 我常用的几个工具软件都让 AI 替代了

有声书制作软件,把下载的单集音频合并成 m4b 文件,并补充元数据,现在文件夹扔给 AI ,一句话说下需求,ai 就自己操作 ffmpeg 给处理了,并会网上搜索资料填充元数据。 音乐元数据刮削软件,自己网上下载的音乐很多元数据缺失或者不对的,需要用这种软件修正,以前用的很烂的软件,经常会失败。现在直接把文件夹扔给 AI 一句话就帮你搞定了。 网页数据抓取,交给国内 AI 干这些太好用了,也是一句话的事情,最终给你结构化的数据。 程序员工具箱类,都懒得打开这些网页了,直接问一下 AI 。 感觉以后个人开发的前景只有游戏这一个方向了,工具类软件完全没用了。

V2EX ·

[分享创造] 写了一个显示字节招聘官网发布时间的小工具

之前写过一个大厂岗位监测工具,因为前端岗位锐减,导致项目没有继续更新。 但是本质上就是确保官网岗位的时效性,做了一个官网显示时效性的小插件。 效果: 地址: https://chromewebstore.google.com/detail/justjob/egeplmeababanmilhfhlfljjjklfchan

V2EX ·

[分享创造] 3 天、12 亿 token:使用 AI 端到端把我用了十几年的股票公式决策系统搬成了 Web 服务,欢迎大家使用反馈

分享一次 "纯 AI 许愿式开发" 的过程。 我自己用了十几年的通达信决策系统(一套股票指标公式,24 类信号)。这次用 AI 花了 3 天、约 12 亿 token ,端到端把它从公式系统重构成前后端服务 —— 连 Docker + 阿里云 ECS 一键部署都是 AI 完成的。我自己一行代码没写、也没细看,全程 "许愿式开发":提需求 → AI 写 → 直接上。用的 CC + GLM 。 网站地址( Web / 手机端都已适配): https://www.zhiguyuntu.com 核心功能(一个展示关键决策信号的页面,十几年的规则体系): https://www.zhiguyuntu.com/help#overview 原本是打算方便自己使用的,为避免误解,说清几点: 这是研究工具,不是荐股软件:所有信号 / 评分只是 "规则化研究结果",不构成对任何证券未来表现的判断; 纯规则算法、无未来函数、可回测,不承诺收益; 不做代客理财、不收荐股费。 后续打算用同样方式扩展到微信小程序、Android/iOS ,也想听听大家意见,欢迎拍砖。

V2EX ·

[问与答] 算力销售赚钱吗

刚才抖音看了一个女的 说弄算力销售 然后评论一个男的截图收入一百四十万 税十七万,看到 V2EX 一个广告 什么 claude 什么企业价一折 看了网站是注册就可以用 不用信用卡,行业应该是个大趋势 如何获利了 目的还是为了我那个 obd 项目的启动资金 几万块就行

V2EX ·

[推广] ChatGPT Plus/Pro 长期稳定充值 直充账户 (可开票)

✅ChatGPT Plus 125 ✅ChatGPT 5x ( 10x ) 660 ChatGPT ✅20x 1150 现在 ChatGPT Pro 订阅额度翻倍🐮 Pro5x 目前最具性价比,是 10 倍 plus 用量了🤔 🤔欢迎 v 友咨询,已服务 600+ v 友 可以 +v(备注 GPT)交流👏 : a2tsdDg4OGs= (悟空 AI) ✅下单网站: https://gptpao.com

Product Hunt ·

AC Bridge

Your smart lights show when Claude Code or Codex needs you.

V2EX ·

[分享创造] ai 强大了以后,感觉大家做产品的人越来越多,于是做了个地方把它们摆出来

最近刷社区,感觉身边动手做东西的人明显变多了:有人下班写个小工具,有人折腾个 App ,小程序,有人把一堆 prompt 攒成智能体。但东西做出来之后,大多就躺在相册、GitHub 或者朋友圈里,过两天连自己都想不起来放在哪。 所以做了个小网站:造梦橱窗 大家的作品集 - 收录大家的网站、小程序、App 与智能体作品 https://idea.v5pc.com/ 想干的事很简单----给作品一个统一的陈列位: 网站、小程序、App 、智能体都能提交,一个表单填完 封面 + 最多 9 张宣传图 按形态、分类浏览,点进去能看到完整介绍、宣传图和跳转入口 有点赞、收藏、评论和榜单 做了 SSR 和 sitemap ,作品能被搜索引擎正常收录。 现在上面作品还很少,基本都是我自己和朋友的数据。 手上正好有作品的,欢迎直接扔上去试试;遇到 bug 或者体验不好的可以尽管提意见。

arXiv ·

LRMoE: Demand-Side Load Re-Calibration for Efficient MoE Training on Memory-Constrained Nodes

arXiv:2610.37720v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models offer scalable capacity for Web applications, but uneven routing creates computation and communication bottlenecks. Existing placement and replication methods redistribute this workload, yet additional expert copies compete with token-related buffers for limited GPU memory. We present LRMoE, a memory-aware MoE training system that jointly recalibrates backward demand and balances the retained workload. During

arXiv ·

Amortized Localized Posterior Inference for Model Calibration with Application to an Ocean Turbulence Closure

arXiv:2610.37731v1 Announce Type: new Abstract: Model discrepancy may prevent a single calibration parameter from reproducing a physical response across the context domain. In addition, uncertainties in observations and contexts affect calibration and must be accounted for and quantified. We construct a family of localized posteriors by weighting observation likelihoods according to their proximity to a target context. Gaussian localization weights incorporate context uncertainty through covaria

arXiv ·

ThinkJev: One Thought, Every Budget for Calibrated Typed Decisions

arXiv:2610.37732v1 Announce Type: new Abstract: Many uses of language models end in a typed decision: a choice among a closed set of options, whose probabilities code can act on. Reading those probabilities from one forward pass is fast but often wrong on decisions that take several steps, such as arithmetic, counting, and date comparison. Letting the model think first fixes most of these errors, but costs seconds per decision instead of milliseconds. To pay for thinking only where it helps, Thi

arXiv ·

OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery

arXiv:2610.37739v1 Announce Type: new Abstract: Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluating them on research-level problems remains challenging. We introduce OpenFrontiers, a cross-disciplinary resource that combines a structured corpus of open research problems with a retrospective benchmark of recently resolved problems in mathematics. The corpus records problem st

arXiv ·

WebAnything: From the Wild Web to Scalable Agent Environments

arXiv:2610.37786v1 Announce Type: new Abstract: Web agents require diverse, executable, and resettable website environments for reproducible training and evaluation. Human-assisted mirrors demand per-site engineering, while generative construction can diverge from specified real websites. Capture-and-replay preserves observations, with interaction coverage constrained by captured content and replay capabilities. We present WebAnything, a fully automated framework that reconstructs source-grounde

arXiv ·

What Does an Ontology Catch? Curated, LLM-Generated and Data-Derived Ontologies as Checkers of LLM Agents over Knowledge Graphs

arXiv:2610.37809v1 Announce Type: new Abstract: LLM agents that answer questions over Web knowledge graphs are increasingly wrapped in checks derived from the graph's ontology, on the assumption that a formal schema makes a reliable judge. Yet a checker can be wrong as well: it can miss errors, and it can flag correct answers and push the agent into "fixing" them. Whether a curated ontology is worth its cost as such a judge, and how it compares with an ontology an LLM writes or a schema mined fr

arXiv ·

Measuring Where Intent Gets Lost in Agentic Smart Contract Synthesis

arXiv:2610.37830v1 Announce Type: new Abstract: AI agents can now write software from a plain-English description, but code that runs is not the same as code that does what was asked. This gap matters most for smart contracts, the programs behind Web3 applications that move money on a blockchain and cannot be fixed once deployed. We ask how to check whether an AI-written contract behaves as it should, and where the requested behavior gets lost. We design an evaluation built on execution rather t

arXiv ·

Detecting Covert Collusion between AI Agents through Partner-Outsider Positive Listening

arXiv:2610.37849v1 Announce Type: new Abstract: AI agents that share a secret convention can coordinate through messages that look innocent, so a monitor that reads only the messages can miss them. We propose a behavioural test: a partner that uses a code reacts to the exact wording of a message, whereas an uninvolved agent placed in its seat does not. Partner--Outsider Positive Listening (PoPLi) is the difference between the two agents in how much their action changes when the message is reword

arXiv ·

Evaluating and improving AI agents for sequencing protocol understanding

arXiv:2610.37851v1 Announce Type: new Abstract: Existing scientific-agent benchmarks rarely evaluate whether agents can reconstruct the exact molecular structures and generation workflows specified by sequencing protocols, a capability critical for analyzing customized sequencing assays. We introduce LibStructBench, a document-grounded benchmark for reconstructing sequencing-library structures and molecular workflows. Our experiments show that frontier agents often produce approximately correct

arXiv ·

Seq@K: Evaluating Language Models Under Sequential Feedback

arXiv:2610.37859v1 Announce Type: new Abstract: Language-model agents differ fundamentally from prior intelligent systems in their ability to learn from natural language in context. This capability enables agents to iteratively refine their answers in response to feedback, a prevalent mode of operation in modern agentic workflows. However, the community primarily ranks models by metrics such as Pass@1 or Pass@K, which cannot capture how they utilize feedback on prior attempts. We introduce Seq@K

arXiv ·

What Constitutes Food Similarity? Visual Representations and Retrieval in Indian Cuisine

arXiv:2610.37867v1 Announce Type: new Abstract: Food similarity underlies retrieval, recommendation, substitution, and other food computing tasks, yet food representations are typically evaluated by identity preservation. We ask what happens to food similarity beyond identity: how different visual representations organize foods into relational neighborhoods, what culinary relationships these neighborhoods reveal or obscure, and how consistently these structures emerge across representations. Ind