Article URL: https://github.com/drasimwagan/mdv Comments URL: https://news.ycombinator.com/item?id=47816629 Points: 2 # Comments: 0
如题，两个都是优秀的copilot自定义第三方api的扩展，但是小白在挑选的时候犯了难，各位用哪个兼容性比较好，我平时用responses接口比较多 1 个帖子 - 1 位参与者 阅读完整话题
除cursor外，还有哪些好用的IDE AI编程工具？ 1、列3-5个，排个序？ 2、这里不含cc和codex的cli。 11 个帖子 - 9 位参与者 阅读完整话题
model_provider = "cliproxyapi" model = "gpt-5.4" model_reasoning_effort = "xhigh" service_tier = "fast" 上面是我codex 模型配置，我看cpa日志，是不会用gmini和claude的供应商，有啥办法在codex会话里面切换或者让cpa自动切换吗 随便再问一下，cpa里面ai供应商的那个前缀配置怎么用啊 2 个帖子 - 2 位参与者 阅读完整话题
Article URL: https://github.com/eph5xx/tweakidea Comments URL: https://news.ycombinator.com/item?id=47815028 Points: 1 # Comments: 0
微软最近释出了预览版 Windows 11 Insider Preview Build 26300.8170，其中一项变化是将 FAT32 分区大小从 32GB 增加到 2TB。FAT32 分区大小限制在 32GB 是微软开发者随手设置的，几十年来一直没变，导致当存储卡和 U 盘容量超过 32GB 时，用户只能选择 exFAT 或 NTFS。现在微软终于移除了这一限制，但该大小限制仍然只在命令行里移除。
哪个有的佬，可以分享一下这个终身许可密钥吗，之前有，结果电脑的系统盘坏了重装系统过后就找不到了。 如有佬可以分享，感谢感谢 1 个帖子 - 1 位参与者 阅读完整话题
排查了好久，很烦，每次测试ssh tunnel都是通的，一连接就报错 1 个帖子 - 1 位参与者 阅读完整话题
仅限insider，真的超值的 9 个帖子 - 8 位参与者 阅读完整话题
AnyRouter的怎么API要怎么接入我的IDE？ 原理：客户端中子代理在请求体里不传递思考参数，haiku请求头不带1M，导致any后端校验不正确，所以请求会错误。 知道原理就好干了，以cch为例。 1.给any的所有请求，追加请求头，写入1M 这个请求头是直接在我IDE（Breezell）的API设置里面添加吗？ 有佬可以发一下请求头JSON吗？ 1 个帖子 - 1 位参与者 阅读完整话题
Download HD Twitter Videos & Images Instantly | Fast, Private Tweet & Profile Media Saver with Twitter Media Downloader Comments URL: https://news.ycombinator.com/item?id=47813269 Points: 1 # Comments: 0
目前可以申请的数字公民项目： 爱沙尼亚 e-Residency 立陶宛 e-Residency 帕劳数字居留（RNS） 哪些可以过 Claude KYC，还有其他推荐的吗？ 14 个帖子 - 7 位参与者 阅读完整话题
在github闲逛，发现一个claude code的自动提取内存的插件，叫claude-mem，大概就是自动根据几个hook，提取内容保存，自动增加内容提问，大概就是这个意思，不过一看provider，只支持御三家，无法填国内的，看着挺好的，就是用不了，实在没国内版本的我就打算后面自己写一个算了，有的话还请佬推荐一下。 顺便说一下这个东西的作用，最近hermes之所以这么火，也是因为他的自学习能力，所谓自学习能力，其实就是内存管理，跟上面的原理是差不多的。所以claude code有了这个，等于变相也成了一个可以自己学习的编程智能体。 4 个帖子 - 3 位参与者 阅读完整话题
Built this around one simple idea: the workflow that wants to execute should not be the same place that decides whether execution may continue. This project puts an external allow/deny boundary before action. Public entry points: * live pilot * commercial request * private deployment There is also a GitHub Marketplace action install surface, but the main point is the boundary model itself: decision stays outside the workflow that is asking to proceed. Looking for feedback from people working on CI/CD, security controls, approval boundaries, and automated execution. Comments URL: https://news.ycombinator.com/item?id=47811161 Points: 2 # Comments: 0
We built AI Subroutines in rtrvr.ai. Record a browser task once, save it as a callable tool, replay it at: zero token cost, zero LLM inference delay, and zero mistakes. The subroutine itself is a deterministic script composed of discovered network calls hitting the site's backend as well as page interactions like click/type/find. The key architectural decision: the script executes inside the webpage itself, not through a proxy, not in a headless worker, not out of process. The script dispatches requests from the tab's execution context, so auth, CSRF, TLS session, and signed headers get added to all requests and propagate for free. No certificate installation, no TLS fingerprint modification, no separate auth stack to maintain. During recording, the extension intercepts network requests (MAIN-world fetch/XHR patch + webRequest fallback). We score and trim ~300 requests down to ~5 based on method, timing relative to DOM events, and origin. Volatile GraphQL operation IDs are detected and force a DOM-only fallback before they break silently on the next run. The generated code combines network calls with DOM actions (click, type, find) in the same function via an rtrvr.* helper namespace. Point the agent at a spreadsheet of 500 rows and with just one LLM call parameters are assigned and 500 Subroutines kicked off. Key use cases: - record sending IG DM, then have reusable and callable routine to send DMs at zero token cost - create routine getting latest products in site catalog, call it to get thousands of products via direct graphql queries - setup routine to file EHR form based on parameters to the tool, AI infers parameters from current page context and calls tool - reuse routine daily to sync outbound messages on LinkedIn/Slack/Gmail to a CRM using a MCP server We see the fundamental reason that browser agents haven't taken off is that for repetitive tasks going through the inference loop is unnecessary. Better to just record once, and get the LLM to generate a script leveraging all the possible ways to interact with a site and the wider web like directly calling backed API's, interacting with the DOM, and calling 3P tools/APIs/MCP servers. Comments URL: https://news.ycombinator.com/item?id=47810533 Points: 5 # Comments: 1
Cloudflare's recent voice agents release provides a free daily tier for Deepgram STT, TTS use. So I created a Voice AI Agent pipeline that runs on Cloudflare workers with Durable Objects and it interfaces with an Arduino ESP32. This lets you bring any LLM to power your Voice AI Toys and Desk companions with STT + TTS handled natively. Comments URL: https://news.ycombinator.com/item?id=47810376 Points: 2 # Comments: 0
Article URL: https://agents.ml Comments URL: https://news.ycombinator.com/item?id=47810052 Points: 2 # Comments: 1
Article URL: https://www.youtube.com/watch?v=Syhgdct_VC4 Comments URL: https://news.ycombinator.com/item?id=47809777 Points: 1 # Comments: 0
I used to run a flash games website (SWF files) years ago. I've made a few games of my own. I'm also an avid gamer and love to play games of all kinds. I'm also a software engineer, and a few days ago I decided I wanted to run a games website again. So I bought the domain gamevibe.us and with the help of Claude I've been vibe-coding one video game every day since. Happy to answer questions, take feedback, etc -- don't hold back, I know it's pretty elementary so far Comments URL: https://news.ycombinator.com/item?id=47808041 Points: 4 # Comments: 1
IT之家 4 月 17 日消息，消息人士 @ camerainsider 昨天在 X 平台透露，适马计划 9 月发布一款 65mm 超大光圈自动对焦镜头新品， 光圈比 F1.2 更大 。 作为参考，适马曾在 2020 年推出过 65mm F2 DG DN 镜头，适配“马徕松”L 卡口 / 索尼 E 卡口，主打全金属镜身、高解析力、紧凑设计。不过这款产品隶属 Contemporary 系列，主打轻巧便携而非极限性能。 同时，目前无反全画幅自动镜头领域，超越 F1.2 光圈的全画幅自动对焦镜头还比较少见，推测适马的这款镜头光圈规格大概率可能是 F1.0，当然也有可能是 F1.1 或 F1.05。