Show HN: ToDoRoulette https://ift.tt/GPyA4b7

Show HN: ToDoRoulette This is a super simple tool to help stop procrastinating by randomly choosing a task to work on. This was built with almost no effort using vibe coding. https://ift.tt/20Ww6BD May 26, 2025 at 01:52AM

Show HN: Generate SVGs with AI https://ift.tt/TxqFS45

Show HN: Generate SVGs with AI https://vectorart.ai May 26, 2025 at 12:47AM

Show HN: I built a chill place online to work on your ideas https://ift.tt/jzBVpec

Show HN: I built a chill place online to work on your ideas I used to watch hundreds of hours of lofi beats on youtube while I was coding, but I got really sick of all the ads. I decided to build a better alternative - It's a configurable space for you to hang out online while you work, with a ton of relaxing music and backgrounds. Its got useful tools built in like a timer to keep track of how long you've been locked in, and a notepad for todos or scribbling down ideas while you work. Honestly this is the first tool I've built that I personally use every day, so I'm hoping some of you out there can get some use out of it too! https://lofizone.com May 25, 2025 at 04:08AM

Show HN: DeepShot – NBA game predictor with 71% accuracy using ML and stats https://ift.tt/Kd9qaHT

Show HN: DeepShot – NBA game predictor with 71% accuracy using ML and stats Hey everyone, I’m an NBA fan and Python dev, and I recently built DeepShot — a machine learning model that predicts NBA game outcomes with about 71% accuracy based on historical stats and rolling performance metrics (EWMA). It features: Real NBA data from Basketball Reference Exponentially Weighted Moving Averages to track momentum Interactive NiceGUI interface with team comparison and predictions Full Python stack and open-source (MIT license) Here’s the GitHub repo: https://ift.tt/BDI8yfP And if you like it, here’s my Buy Me a Coffee: buymeacoffee.com/saccofrancesco Would love any feedback — especially from folks who’ve built sports models or worked on real-time stat tools. Also open to ideas on where to take this next (player-level modeling? betting advice dashboard?). Thanks! https://ift.tt/BDI8yfP May 25, 2025 at 02:30AM

Show HN: 1min Workouts for People Who Sit All Day https://ift.tt/whJv9A7

Show HN: 1min Workouts for People Who Sit All Day I am a software developer and in the last few months after recently becoming a father I was barely finding time for a proper workout. Recently I was reading about new research on Snack Exercises and how beneficial mini workouts of less than 2mins every so often, during the day are to our body. So, I decided to build an iOS App for me and others to help with this. The app generates a list of exercises that I need to tick to complete daily or loose my streak. The algorithm takes into account muscle groups and balancing the exercises to hit most main muscles. I also stayed going through all exercises and adding a couple of alternative exercises in case I don't feel like the recommended exercise. Since I'm not a trainer I commissioned professional exercise posture video guides and animations by an exercise expert which I attached to each exercise. I uploaded the app on the app store for free and no ads. If this is something that interests you, I want to hear how you balance a long day on your desk vs exercise. https://shortreps.com May 25, 2025 at 02:11AM

Show HN: Can AI Help Designers Ideate Better? We Spent 5 Wks Finding Out https://ift.tt/QiFt6s2

Show HN: Can AI Help Designers Ideate Better? We Spent 5 Wks Finding Out We set out to answer a simple but deep question: Can AI actually practically help product designers improve during the discovery and ideation phase of the design process? So we spent 5 weeks running an experiment. We mapped every tool we use for discovery: Mobbin, Dribbble, Pinterest, Twitter, Behance We broke down typical design thinking and brainstorming workflows We reviewed every prototyping or idea-capturing tool we’ve used Then we tried building lightweight AI workflows with various LLM tools and frameworks Result: Yes. Used well, AI can significantly improve design thinking — especially for junior/mid-level designers — by offering faster idea generation, design critiques, and creative merges. Out of that research, we built Moonchild: A discovery-stage design ideation tool that: Generates thoughtful UI concepts from minimal prompts Allows asking design questions and getting structured critique Merges styles, flows, and interaction patterns from multiple directions Outputs great Figma-ready screens and UX flows, fast Try it (private beta): https://moonchild.ai Use code 'hackernews' for early access. Would love feedback — especially from product designers, PMs, and UX folks doing early-stage work. May 25, 2025 at 12:36AM

Show HN: Advanced Chunking in JavaScript/TypeScript with Chonkie https://ift.tt/fJ6pF7j

Show HN: Advanced Chunking in JavaScript/TypeScript with Chonkie Hi HN, We’re Shreyash and Bhavnick. We built Chonkie, an open-source library for advanced chunking and embedding of text and code. It was previously Python-only, but we just released a TypeScript version: https://ift.tt/0x6eZ4K Many AI projects in JS/TS (like those using Vercel's AI SDK or Mastra) rely on basic text splitters. But better chunking = better retrieval = better performance. That’s what Chonkie is built for. Current native chunkers (in TS): - Code Chunker – handles Python, TypeScript, etc. - Recursive Chunker – rule-based, hierarchical splitting - Token Chunker – split by token count (fully customizable) - Sentence Chunker – split on sentence boundaries. Delimiters are customizable, so it works for multiple languages. All chunkers support custom tokenizers, chunk overlap, delimiters, and more. Coming soon in native TS (already available via the API client): - Semantic Chunker – splits texts wherever it detects a shift in meaning. - SDPM Chunker – merges semantically similar disjoint chunks - Late Chunker – generates context-aware embeddings for each chunk - Slumber Chunker – LLM-refined recursive chunks. Significantly reduces token usage (and thus cost) while maximizing chunk quality. - Embeddings Refinery - Embed chunks with any embedding model - Overlap Refinery – Create overlaps between consecutive chunks for better context preservation. Chonkie is free, open-source, and MIT licensed. GitHub: https://ift.tt/0x6eZ4K We’d love your feedback, ideas, or contributions. Thanks! May 24, 2025 at 01:33AM