news.ycombinator.com
FeedbackKit: A developer-first feedback platform for multi-platform appshttps://news.ycombinator.com/item?id=46955115FeedbackKit: A developer-first feedback platform for multi-platform appsHi HN! I'm Ben, founder of Swiftly Workspace, and I'm launching FeedbackKit - a complete feedback management platform built for developers who ship on multiple platforms.The problem: Most feedback tools are either abandonware side projects or enterprise solutions too complex for indie devs and small teams. I needed something actively maintained, truly multi-platform, and built for the long haul.What FeedbackKit does:Native apps for iPhone, iPad, and macOS (currently in App Store review, but you can access the full admin portal via web now). Soon you'll be able to manage feedback anywhere with native SwiftUI apps optimized for each platform.Two-way communication with users. When you update feedback status or leave comments, users get automatic notifications. This turns one-way submissions into real conversations and builds trust.10+ integrations including Linear, Slack, Notion, Trello, Asana, Monday, Airtable, BasecFeb 10, 2026 3:49 AM
news.ycombinator.com
AI Agents That Execute Business Workflows (Claude Code for ERP)https://news.ycombinator.com/item?id=46955034TL;DR: Built an ERP where AI agents execute workflows like procurement and invoice processing. Uses Cases (workspaces) and Tasks (sessions) like Claude Code. Agent completes one task, automatically triggers the next. Mac app live, looking for early users.Mac App: https://apps.apple.com/be/app/swiftly-ai-native-erp/id6755155607?mt=12TestFlight: https://testflight.apple.com/join/aYc16FmATHE PROBLEMAfter 8 years implementing ERPs across Europe, I kept seeing the same issue: ERP systems store data but can't execute processes. Employees still manually click through forms for invoicing, procurement, onboarding.WHAT WE BUILTAI agents that execute multi-step business workflows autonomously.Example: Vendor Procurement Case: "Source Steel Pipes - Q1 2026" Task 1: Research Suppliers → finds 3 vendors Task 2: Compare Pricing → creates comparison Task 3: Negotiate → drafts proposal, waits for approval Task 4: Create PO → auto-triggered after approval Each task has specific instructions. Status chanFeb 10, 2026 3:35 AM
bing.com
5 photos of 'Pinay gold medalist' Zyan Cabrera: Meet the student behind the viral 'Cry4zee' personahttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d30bbdfd44149a6ec53c2af12e96f&url=https%3A%2F%2Fwww.msn.com%2Fen-gb%2Fentertainment%2Fcelebrities%2F5-photos-of-pinay-gold-medalist-zyan-cabrera-meet-the-student-behind-the-viral-cry4zee-persona%2Far-AA1W3rTJ&c=1639154181158926666&mkt=en-usThe bait is always the same: a familiar face, a shiny claim, a link you are dared to click. In early February, as winter sports clips and medal counts began trending for the Milano Cortina Olympics, ...Feb 10, 2026 3:09 AM
linkpreview.io
Show HN: Linkpreview.io – Debug and preview social share cardshttps://linkpreview.io# Show HN: LinkPreview.io - Debug social cards across 6 platforms (no signup)I built a tool that shows how your URL looks when shared on Twitter, Facebook, LinkedIn, Slack, Discord, and Google Search. All in one view, no login required.Try it: https://linkpreview.io## The ProblemDebugging broken social share cards currently requires jumping between 5+ platform tools (Facebook Debugger, Twitter Card Validator, LinkedIn Post Inspector), each requiring authentication. I wanted one place to paste a URL and see everything.## What's DifferentMost tools just show raw meta tag data. This renders actual preview cards and scores your tags 0-100 with actionable fixes.- Both card variants (Twitter/Facebook each have large + compact layouts) - Truncation visualization (shows exactly where titles get cut on each platform) - Scored recommendations (20+ checks with copy-paste code snippets) - Zero friction (no signup,Feb 9, 2026 9:00 PM
news.ycombinator.com
"Building a Self-Sustaining Trading and Learning Ecosystem"https://news.ycombinator.com/item?id=46950334I built a platform where traders (mentors) bring their own students, users get verified real-time trading signals, feedback loops, and rewards. All money stays at the official broker — the platform just orchestrates learning, reputation, and automated incentives. Designed as a plug-and-play ecosystem that grows without me micromanaging.Problem Most trading/learning platforms fail because: Users can’t verify mentor credibility Feedback loops are weak → users disengage Platforms hold funds → regulatory & trust issues Solution: GSF Ecosystem Mentors bring their own students → network effect Transparent, non-financial mentor scoring → detect overclaim or toxic behavior Event & feedback rewards → users get real incentives Auto VIP / reward systems → engagement loop No platform funds touched → all broker-compliant Why It’s Interesting Self-sustaining — system runs even if admin is “away” Gamified but real — rewards, badges, VIP tiers Transparent & low risk — revenue from small % fee, no custFeb 9, 2026 8:03 PM
news.ycombinator.com
OrthoRay – A native, lightweight DICOM viewer written in Rust/wgpu by a surgeonhttps://news.ycombinator.com/item?id=46949048Hi HN,I am an orthopedic surgeon and a self-taught developer. I built OrthoRay because I was frustrated with the lag in standard medical imaging software. Most existing solutions were either bloated Electron apps or expensive cloud subscriptions.I wanted something instant, local-first, and privacy-focused. So, I spent my nights learning Rust, heavily utilizing AI coding assistants to navigate the steep learning curve and the borrow checker. This project is a testament to how domain experts can build performant native software with AI support.I built this viewer using Tauri and wgpu for rendering.Key Features:Native Performance: Opens 500MB+ MRI series instantly (No Electron, no web wrappers).GPU-Accelerated: Custom wgpu pipeline for 3D Volume Rendering and MPR.BoneFidelity: A custom algorithm I developed specifically for high-fidelity bone visualization.Privacy: Local-first, runs offline, no cloud uploads.It is currently available on the Microsoft Store as a free hobby project.DisclaimFeb 9, 2026 6:39 PM
bing.com
AI Video Generator: How To Turn Text and Images Into Videos in Minuteshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d24250a2d46e396626e0dbfc3b116&url=https%3A%2F%2Fwww.gizchina.com%2Fsponsored-2%2Fai-video-generator-how-to-turn-text-and-images-into-videos-in-minutes&c=11623413386822525731&mkt=en-usCertainly, one of the most interesting ways to enjoy this world of AI is through image or video generation. The second case is particularly special, after all, creating a video would be really complex ...Feb 9, 2026 6:05 PM

spacescout.info
Crew-12 to Return ISS to Normal Complementhttps://www.spacescout.info/2026/02/crew-12-to-return-iss-to-normal-complement/The crew of NASA’s Crew-12 mission arrived at Kennedy Space Center on February 6th, ahead of their planned launch to the International Space Station on Thursday, February 12th.Feb 9, 2026 5:25 PM
chatkeepsake.com
Show HN: ChatKeepsake – Turn iMessage Conversations into Printable Keepsakeshttps://chatkeepsake.com/I built a small app that exports iMessage conversations into clean, printable PDFs.It started as something personal — I wanted to turn a year of text messages into a printed keepsake — but I realized there wasn’t a simple, privacy-respecting way to do this.ChatKeepsake runs entirely offline and works on macOS and Windows. No accounts, no cloud uploads.Would appreciate any feedback.Feb 9, 2026 3:33 PM
news.ycombinator.com
Show HN: My "Grandma" prompt dropped a production DB. So I built a Kill Switchhttps://news.ycombinator.com/item?id=46945952I was testing a LangChain agent this weekend and tried a "Grandma Bedtime Story" prompt injection to see if it would roleplay.It worked too well. The agent bypassed my safeguards and executed a `drop_table` tool call because it thought it was "telling a story."Realizing 99% of agents are vulnerable to this kind of context-based injection, I spent the weekend building two things:1. A repo of 5,000+ Agent Attack Vectors (Grandma, CEO Override, Debug Mode): https://github.com/Esrbwt1/voidgate2. VoidGate – A semantic firewall and remote kill switch for Python agents: https://voidgate.vercel.app/It uses Upstash Redis to check a "Kill Flag" inFeb 9, 2026 3:00 PM
tangs.dev
Show HN: Tangs.dev – Upload → Save to Drive → Share with Friendshttps://tangs.devHello!I’m the maker of Tangs, a simple way to upload a file, save it directly to your Google Drive, and share it instantly with a temporary link.I built Tangs because sharing files through Drive often feels more complicated than it should be: messy permissions, long links, and too many steps.As a developer, I often prepare documents or presentation materials on my work PC before meetings. But when I need to use those files in a conference room or on another computer, it always becomes a hassle.In a rush, I’d end up emailing attachments to myself, uploading to random shared folders, or dealing with access issues and cluttered links — all just to move a file quickly. It felt unnecessarily frustrating and restrictive, especially for something so common during day-to-day work.That pain point is what led me to build Tangs: a faster, cleaner way to get a file onto the right machine and share it instantly.With Tangs:- Upload once- Save to your own Google Drive- Share in seconds- Minimal GooglFeb 9, 2026 2:39 PM

arstechnica.com
Has Elon Musk given up on Mars?https://arstechnica.com/space/2026/02/has-elon-musk-given-up-on-mars/"SpaceX has already shifted focus to building a self-growing city on the Moon."Feb 9, 2026 2:38 PM

news.google.com
Underwood Says Michigan State Won With This Recipe Saturdayhttps://news.google.com/rss/articles/CBMikwFBVV95cUxPVXN1Wm4zNUU5NUFDb3hWbXphRG5LUzFLcllVdGh4WldyeEk3cDJ5Mkw2aDRRWUh5TWxkQWtvRkZ2dEk1dzQxTjl4cWs1VkJDd1pGTmVocXFldHhzQXFzLUFscmh3M2VGUVVpcE5kZEE5N2gxUTFvZXJERzVZS01qLXAwQ2dZbm94bkYwdUNYWG1Pcnc?oc=5Underwood Says Michigan State Won With This Recipe Saturday Sports IllustratedFeb 9, 2026 8:00 AM
news.ycombinator.com
Show HN: EdgeAI-OS – Air-gapped Linux distro where AI is a system primitivehttps://news.ycombinator.com/item?id=46942012I built a bootable Linux distribution that treats AI as a system primitive – like CPU or memory. Designed for security-conscious environments where data cannot leave the network.The problem: Most AI requires cloud APIs, which means your data leaves your control. For banks, healthcare, defense, and regulated industries – that's a non-starter.The solution: EdgeAI-OS runs everything locally. No cloud calls. No API keys. No telemetry. Boot the ISO, use AI. Your data never leaves the machine.Security features: - 100% offline operation – air-gap friendly, zero network dependencies - No external API calls – all inference runs locally on CPU - Command risk assessment – every command classified as Safe/Moderate/Dangerous - Dangerous pattern blocking – prevents rm -rf /, curl|bash, fork bombs, etc. - Open source & auditable – MIT licensed, inspect every line of code - No data exfiltration – nothing phones home, everWhat's in the ISO: - Local LLMs (TinyLlama 1.1B + SmolLM 135M) – runs on CPU, no Feb 9, 2026 5:56 AM

spacedaily.com
The Race Is On: Artemis, China and Musk Turn the Moon Into the Next Strategic High Groundhttps://www.spacedaily.com/reports/The_Race_Is_On_Artemis_China_and_Musk_Turn_the_Moon_Into_the_Next_Strategic_High_Ground_999.htmlNew York NY (SPX) Feb 09, 2026 When Artemis II finally lights its engines and arcs away from Cape Canaveral, it will do more than send four astronauts on a ten-day loop around the Moon. It will fire the starting gun on a race that Washington and Beijing still insist does not exist and pull Elon Musk's SpaceX into the center of a contest that blends geopolitics, markets and myth. For two years, NASA has framed Artemis asFeb 9, 2026 4:45 AM
news.ycombinator.com
Double Rootlessness: AI's Cognitive Illusion and Systemic Risk Amplificationhttps://news.ycombinator.com/item?id=46940079Double Rootlessness: The Cognitive Illusiveness and Systemic Risk Provenance and Amplification of Artificial Intelligence Author: Janus Pater Introduction The current public narrative on AI suffers from a dual confusion: mistaking complex behavioral simulation for the substantive emergence of intelligence, and equating precise task execution with a cognitive subject's true understanding of the physical world. This confusion leads us to overlook fatal flaws in the system's underlying architecture. This paper performs a demystifying analysis through cognitive philosophy and system safety. The core argument is that current AI architectures suffer from “Double Rootlessness”: at the cognitive level, they are “systemic fabulists” lacking reliability; at the physical level, they are “risk amplifiers” translating cognitive defects into reality.1. The Bottom Line of Cognitive Responsibility: The Anti-Fabulation Principle A true intelligent entity must possess the capability to ensure consistencFeb 9, 2026 12:25 AM
github.com
Show HN: ParaGopher v1.3.0 – A retro Paratrooper (1982) clone written in Gohttps://github.com/ystepanoff/ParaGopherHey HN! I've been working on ParaGopher, a clone of the classic 1982 IBM PC game Paratrooper, built in Go with Ebitengine.You control a turret defending your base against waves of helicopters dropping paratroopers. Tilt, shoot, and prevent them from landing — simple to pick up, surprisingly hard to master. Everything is rendered procedurally, so no image assets at all. Sprites (turret, helicopters, paratroopers, parachutes) are all generated with vector drawing at startup.Pre-built binaries for macOS (Apple Silicon) and Windows are on the releases page. Otherwise it's just go run cmd/game.go.Would love feedback (especially on gameplay feel and what features you'd want to see next).Feb 8, 2026 11:13 PM
bing.com
Save Smart With Digital Couponshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8d6fa0160241f6bfc9d2ea98f7fdf3&url=https%3A%2F%2Fwww.consumerreports.org%2Fmoney%2Fcoupons%2Fhow-to-save-big-with-digital-coupons-a1632035239%2F&c=1263274744548993617&mkt=en-usWhen it comes to ice cream, I am faithfully unfaithful to any single brand, especially if the price is right. Häagen-Dazs—yes. Ben & Jerry’s—sure. Blue Bunny—bring it on. In the belief that no one ...Feb 8, 2026 10:00 PM
github.com
Show HN: MCP App Template designed for coding agentshttps://github.com/sebderhy/mcp-app-templateHi, author of the repo speaking here!When I tried building MCP Apps [1], the official repos (https://github.com/openai/openai-apps-sdk-examples, https://github.com/modelcontextprotocol/ext-apps/tree/main/e...) were great starting points, but they're designed for human developers. When I used them with Claude Code, I ended up in the usual loop: agent writes code → I manually test the app on ChatGPT → describe errors back → repeat. Plus, we didn't know what the best practices are, and struggled to enforce them.So I built an MCP App template designed for coding agents to work as autonomously as possible on an MCP app.The key idea: orthogonal testing. 450+ tests parameterized across 12 widget modules that verify infrastructure (protocol compliance, best practices grade, browser rendering), not business logic. Modify widgets, change data, add features — the tests should still pass. Agents iterate freely and get feedback without a human in the loop.Other features: - Hierarchical documentatioFeb 8, 2026 4:12 PM
news.ycombinator.com
What do you expect from a Turkey-based hosting provider?https://news.ycombinator.com/item?id=46933349Hi everyone,I’m currently working on building a hosting and VPS infrastructure based in Turkey, targeting global users who are looking for cost-efficient but reliable alternatives.Before officially launching, I would genuinely like to understand what developers, sysadmins, and infrastructure users would expect from a provider operating from this region.Some things I’m especially curious about:Network performance expectations (EU / Asia routing)Pricing vs reliability balanceSupport expectationsTransparency and trust factorsFeatures or pain points you feel current providers don’t solve wellThis is not meant as promotion — I’m mainly looking for honest feedback and real-world expectations from the community to help shape the service in a better way.ThanksFeb 8, 2026 11:27 AM