Show HN: Atari Missile Command Game Built Using AI Gemini 2.5 Pro https://ift.tt/CY3RX0w

Show HN: Atari Missile Command Game Built Using AI Gemini 2.5 Pro A modern HTML5 canvas remake of the classic Atari game from 1980. Defend your cities and missile bases from incoming enemy attacks using your missile launchers. Initially built using the Google Gemini 2.5 Pro AI LLM model. https://ift.tt/rM0o45w April 7, 2025 at 11:48AM

Show HN: Lunon – Instant model switching across LLMs https://ift.tt/b89BAdw

Show HN: Lunon – Instant model switching across LLMs Hey HN! We built Lunon to make LLM development way less of a headache. Ever wanted to see how different models handle the same prompt without all the setup hassle? That's what we fixed. Our API lets you compare Claude, GPT, Mistral and others in real-time with just a few lines of code. No more complex infrastructure or managing multiple API connections - we handle all that boring stuff behind the scenes. Plus, you can cut costs by intelligently routing requests to the right model for each task. Use the powerful (expensive) models only when you really need them. If you're building with LLMs and tired of the integration headaches, would love to hear feedback! https://lunon.com/ April 11, 2025 at 11:46PM

Show HN: I built a tool to manage and compare credit card rewards https://ift.tt/mVTsP9Y

Show HN: I built a tool to manage and compare credit card rewards This is a free tool that helps you manage and visualize your credit card rewards across different categories. You can input the cards in your wallet and see how they complement each other, spot gaps in your setup, and also see the best card to use for a given merchant. I’m also a founder at OneCard, where we’re building a smart card that’ll eventually handle all of this automatically, routing each purchase to the best card in real-time. Would love feedback from the HN community! https://ift.tt/wZkp8d1 April 11, 2025 at 02:54AM

Show HN: Calculate confidence score for OpenAI JSON output https://ift.tt/Qew02mV

Show HN: Calculate confidence score for OpenAI JSON output https://ift.tt/W4zw2Gm April 10, 2025 at 08:46PM

Show HN: I built an app that reduces podcast preparation effort by 95% + https://ift.tt/Wi5X86S

Show HN: I built an app that reduces podcast preparation effort by 95% + https://ift.tt/zQ9qYT0 April 10, 2025 at 11:22PM

Show HN: Aqua Voice 2 – Fast Voice Input for Mac and Windows https://ift.tt/1HRvzZT

Show HN: Aqua Voice 2 – Fast Voice Input for Mac and Windows Hey HN - It’s Finn and Jack from Aqua Voice ( https://withaqua.com ). Aqua is fast AI dictation for your desktop and our attempt to make voice a first-class input method. VIDEO: https://ift.tt/GjA615i TRY IT: https://ift.tt/tdoNjhs Finn is uber dyslexic and has been using dictation software since sixth grade. For over a decade, he’s been chasing a dream that never quite worked — using your voice instead of a keyboard. Our last post ( https://ift.tt/RA5eBXU ) about this really resonated - though it turned out that version of Aqua was a better demo than product. But it gave us (and others) a lot of good ideas about what should come next. Since then, we’ve remade Aqua from scratch for speed and usability. It now lives on your desktop, and it lets you talk into any text field -- Cursor, Gmail, Slack, even your terminal. It starts up in under 50ms, inserts text in about a second (sometimes as fast as 450ms), and has state-of-the-art accuracy. It does a lot more, but that’s the core. We’d love your feedback — and if you’ve got ideas for what voice should do next, let’s hear them! https://withaqua.com April 9, 2025 at 10:01PM

Show HN: I built a tool that deconstructs websites to reveal their tech stack https://ift.tt/b32g6az

Show HN: I built a tool that deconstructs websites to reveal their tech stack Hi HN, I built https://unbuilt.app to solve a problem I frequently faced as a developer: identifying the technology stack behind websites, especially those using newer frameworks and tools. While existing solutions rely on pre-saved data or signature databases, Unbuilt performs a fresh analysis by actually loading and examining the website code in real-time. This means it can detect cutting-edge technologies that often get missed by other analyzers. Technical details: - Uses Playwright to visit sites and analyze their resources - Queue-based architecture for handling concurrent requests - Optimized patterns for detecting modern frameworks (Next.js, Vite, React Compiler, etc.) - Dual-layer caching system for both performance and result sharing The tool is completely open-source and free to use. There are no premium tiers or usage limits. I built it because I believe developers deserve better tools for understanding the web ecosystem. I'd appreciate any feedback, particularly on detection accuracy and the types of technologies you'd like to see added. If you're interested in contributing, all pattern detection logic is designed to be easily extensible. Link to repo: https://ift.tt/5EHXmIG https://unbuilt.app/ April 9, 2025 at 10:57PM