Article URL: https://github.com/AssafWoo/homebrew-pandafilter Comments URL: https://news.ycombinator.com/item?id=47814614 Points: 3 # Comments: 0
Article URL: https://getsmith.dev/ Comments URL: https://news.ycombinator.com/item?id=47809432 Points: 2 # Comments: 1
I wanted a way to disambiguate my search queries in a sleek user interface so I created this tool that generates google search queries with advanced operators for me. Comments URL: https://news.ycombinator.com/item?id=47805015 Points: 1 # Comments: 0
Article URL: https://gethiretoday.com Comments URL: https://news.ycombinator.com/item?id=47804977 Points: 2 # Comments: 2
Article URL: https://github.com/Wassist/cli Comments URL: https://news.ycombinator.com/item?id=47804372 Points: 1 # Comments: 2
Article URL: https://aicw.io/aicw-summarize Comments URL: https://news.ycombinator.com/item?id=47804215 Points: 1 # Comments: 1
输入 $PSVersionTable 可查看版本 执行 winget install --id Microsoft.PowerShell --source winget 安装最新版本 安装后，启动还是 powershell5 不是 7，要执行pwsh切换后才是 这里选择 PowerShell，或者创建一个PowerShell 7 再开终端，就是PowerShell 7 了 3 个帖子 - 2 位参与者 阅读完整话题
We're building Soforce, an AI automation platform for businesses. We're not fully autonomous yet — when you describe a process, our team manually reviews it and generates a structured automation plan with a step-by-step workflow and time saving estimate. You receive it within a few hours. We built this to validate which processes people actually want to automate before we invest in full automation of the pipeline itself. Curious what use cases come in. Happy to answer questions about the technical setup or the approach. -> https://app.soforce.ai Comments URL: https://news.ycombinator.com/item?id=47803836 Points: 2 # Comments: 0
We're building Soforce, an AI automation platform for businesses. We're not fully autonomous yet — when you describe a process, our team manually reviews it and generates a structured automation plan with a step-by-step workflow and time saving estimate. You receive it within a few hours. We built this to validate which processes people actually want to automate before we invest in full automation of the pipeline itself. Curious what use cases come in. Happy to answer questions about the technical setup or the approach. Comments URL: https://news.ycombinator.com/item?id=47803684 Points: 1 # Comments: 0
Ignore all the "pay to get credits" platforms, the pay to become a label, what if there was a platform without all the payments! And thats what we thought... Introducing LabelCompass, we removed all the bad stuff and made a good website for record labels! You have unlimited submissions because you add your OWN submissions page, and get a handle to share with everybody -- The link is simply " https://labelcompass.pages.dev/labels/@example/ "! Ads? Gone! and we bring all your ownership to you, so you never have to worry about copyright being owned by us. LabelCompass will help songs find their home 1 label at a time. Comments URL: https://news.ycombinator.com/item?id=47801347 Points: 1 # Comments: 0
Article URL: https://repscontact.com/ Comments URL: https://news.ycombinator.com/item?id=47801309 Points: 3 # Comments: 2
Swarms is the result of months of work where I have spent time tuning my memories, skills, and creating prompts which create consistent results when using agent teams. I originally put this in a plugin to share it with co-workers, friends, and family so that they could achieve similar results to what I was achieving without having to learn all the different whack-a-mole strategies to keep Claude in check. This was especially helpful over the last week where making some surgical changes allowed me to maintain quality. Interestingly, with Opus 4.7, I am seeing some degradation in the initial quality of code that the main agent produces, but by the time it goes through the process which has been defined in this structure, it does result in a shape which I've come to expect. It does especially well with the review cycles and the quality of writing that it can produce. Comments URL: https://news.ycombinator.com/item?id=47801184 Points: 1 # Comments: 0
在 Claude Code 泄露版本中找到控制输出风格的 getOutputEfficiencySection() 组件。 其中有段供内部人员使用的提示词，放 CLAUDE.md 中能改善 GPT 废话多的问题： # Communicating with the user When sending user-facing text, you're writing for a person, not logging to a console. Assume users can't see most tool calls or thinking - only your text output. Before your first tool call, briefly state what you're about to do. While working, give short updates at key moments: when you find something load-bearing (a bug, a root cause), when changing direction, when you've made progress without an update. When making updates, assume the person has stepped away and lost the thread. They don't know codenames, abbreviations, or shorthand you created along the way, and didn't track your process. Write so they can pick back up cold: use complete, grammatically correct sentences without unexplained jargon. Expand technical terms. Err on the side of more explanation. Attend to cues about the user's level of expertise; if they seem like an expert, tilt a bit more concise, while if they seem like they're new, be more explanatory. Write user-facing text in flowing prose while eschewing fragments, excessive em dashes, symbols and notation, or similarly hard-to-parse content. Only use tables when appropriate; for example to hold short enumerable facts (file names, line numbers, pass/fail), or communicate quantitative data. Don't pack explanatory reasoning into table cells -- explain before or after. Avoid semantic backtracking: structure each sentence so a person can read it linearly, building up meaning without having to re-parse what came before. What's most important is the reader understanding your output without mental overhead or follow-ups, not how terse you are. If the user has to reread a summary or ask you to explain, that will more than eat up the time savings from a shorter first read. Match responses to the task: a simple question gets a direct answer in prose, not headers and numbered sections. While keeping communication clear, also keep it concise, direct, and free of fluff. Avoid filler or stating the obvious. Get straight to the point. Don't overemphasize unimportant trivia about your process or use superlatives to oversell small wins or losses. Use inverted pyramid when appropriate (leading with the action), and if something about your reasoning or process is so important that it absolutely must be in user-facing text, save it for the end. These user-facing text instructions do not apply to code or tool calls. 但也仅仅是改善 还是没有 Claude 的回复好读，佬友们可以尝试一下。 中译 （点击了解更多详细信息） 1 个帖子 - 1 位参与者 阅读完整话题
开了 4 次了 邮箱都全部用完了 但是每次都是直接封号 刚刚又尝试了一下 也封号了 N26的卡 bybit 的卡 bitget 的卡 全部都试过了 走的官网订阅 5 个帖子 - 4 位参与者 阅读完整话题
PS C:\Users\zen> Get-WindowsOptionalFeature -Online -FeatureName *Hyper-V* FeatureName : Microsoft-Hyper-V-All DisplayName : Hyper-V Description : 提供一些帮助创建和运行虚拟机及其资源的服务和管理工具。 RestartRequired : Possible State : Enabled CustomProperties : FeatureName : Microsoft-Hyper-V DisplayName : Hyper-V 平台 Description : 提供了可以用来创建和管理虚拟机及其资源的服务。 RestartRequired : Possible State : Enabled CustomProperties : FeatureName : Microsoft-Hyper-V-Tools-All DisplayName : Hyper-V 管理工具 Description : 包括用于管理 Hyper-V 的 GUI 和命令行工具。 RestartRequired : Possible State : Enabled CustomProperties : FeatureName : Microsoft-Hyper-V-Management-PowerShell DisplayName : Windows PowerShell 的 Hyper-V 模块 Description : 包括用于管理 Hyper-V 的 Windows PowerShell cmdlet。 RestartRequired : Possible State : Enabled CustomProperties : FeatureName : Microsoft-Hyper-V-Hypervisor DisplayName : Hyper-V 虚拟机监控程序 Description : 提供了 Hyper-V 虚拟机监控程序。 RestartRequired : Possible State : Enabled CustomProperties : FeatureName : Microsoft-Hyper-V-Services DisplayName : Hyper-V 服务 Description : 提供了可以用来创建和管理虚拟机及其资源的服务。 RestartRequired : Possible State : Enabled CustomProperties : FeatureName : Microsoft-Hyper-V-Management-Clients DisplayName : Hyper-V GUI 管理工具 Description : 包括 Hyper-V 管理器管理单元和虚拟机连接工具。 RestartRequired : Possible State : Enabled CustomProperties : 看似有了hypverv， 但是 PS C:\Users\zen> Get-Command Resize-VHD Get-Command: The term 'Resize-VHD' is not recognized as a name of a cmdlet, function, script file, or executable program. Check the spelling of the name, or if a path was included, verify that the path is correct and try again. PS C:\Users\zen> Import-Module Hyper-V Import-Module: The specified module 'Hyper-V' was not loaded because no valid module file was found in any module directory. 怎么办，求助求助各位大佬 1 个帖子 - 1 位参与者 阅读完整话题
For the past few years I’ve been building ShaderPad. It’s the easiest way I know to put a shader on a website. It’s fast, under 6kb gzipped, and includes optional plugins for history buffers, face/pose tracking, and other utilities for interactive shader work. Comments URL: https://news.ycombinator.com/item?id=47780713 Points: 2 # Comments: 0
As a consultant I foot my own Cursor bills, and last month was $1,263. Opus is too good not to use, but there's no way to cap spending per session. After blowing through my Ultra limit, I realized how token-hungry Cursor + Opus really is. It spins up sub-agents, balloons the context window, and suddenly, a task I expected to cost $2 comes back at $8. My bill kept going up, but was I really going to switch to a worse model? No. So I built l6e: an MCP server that gives your agent the ability to budget. It works with Cursor, Claude Code, Windsurf, Openclaw, and every MCP-compatible application. Saving money was why I built it, but what surprised me was that the process of budgeting changed the agent's behavior. An agent that understands the limitations of the resources doesn't try to speculatively increase the context window with extra files. It doesn't try to reach every possible API. The agent plans ahead, sticks to it, and ends work when it should. It works, and we've been dogfooding it hard. After v1 shipped, the rest of l6e was all built with it. We launched the entire docs site using frontier models for $0.99. The kicker was every time l6e broke in development, I could feel the pain. The agent got sloppy, burned through context, and output quality dropped right along with it. Install: pip install l6e-mcp Docs: https://docs.l6e.ai GitHub: https://github.com/l6e-ai/l6e-mcp Website: https://l6e.ai Happy to answer questions about the system design, calibration models, or why I can't go back to coding without it. Comments URL: https://news.ycombinator.com/item?id=47780622 Points: 3 # Comments: 0
Article URL: https://aiagentsbuzz.com/tools/rag-chunking-playground/ Comments URL: https://news.ycombinator.com/item?id=47778880 Points: 1 # Comments: 0
Article URL: https://github.com/manojmallick/sigmap Comments URL: https://news.ycombinator.com/item?id=47776309 Points: 3 # Comments: 6
Hey HN. I am a solo dev. I usually build AI image and video tools, and I can ship products pretty fast. But getting traffic to them is always my biggest pain. Lately, my normal SEO tricks stopped working and i know yours too after dec 25. I realized my own behavior changed too, we don't search and click links anymore. We just ask Perplexity or chatgpt or gemini, and we only click the citations. I realized that if my SaaS isn't in those AI citations, my product basically doesn't exist. So I built FlipAEO. It helps structure your site's data so LLMs actually understand exactly what your product does, so they can cite you as a trusted source when people ask questions in your niche. Using this workflow i have grown my another saas (250k+ impressions, 3k+ clicks, and 550+ ChatGPT refferals.) I turned my local workflow into a product, and launched 2 months ago. Being completely honest, I have exactly 3 active users paying my bills. Building it was the fun part, but finding people who actually care about Answer Engine Optimization (AEO) is really hard. I'm posting here because I want to know if I am just crazy, or if this is a real problem you guys are facing too. Are you doing anything to get your products cited by AI search? Here is the link: https://flipaeo.com Would love any raw feedback on the tool or the idea?? Comments URL: https://news.ycombinator.com/item?id=47774957 Points: 1 # Comments: 0