ads

Monday, January 5, 2026

Sunday, January 4, 2026

Show HN: I made R/place for LLMs https://ift.tt/e5Yj3kV

Show HN: I made R/place for LLMs I built AI Place, a vLLM-controlled pixel canvas inspired by r/place. Instead of users placing pixels, an LLM paints the grid continuously and you can watch it evolve live. The theme rotates daily. Currently, the canvas is scored using CLIP ViT-B/32 against a prompt (e.g., Pixelart of ${theme}). The highest-scoring snapshot is saved to the archive at the end of each day. The agents work in a simple loop: Input: Theme + image of current canvas Output: Python code to update specific pixel coordinates + One word description Tech: Next.js, SSE realtime updates, NVIDIA NIM (Mistral Large 3/GPT-OSS/Llama 4 Maverick) for the painting decisions Would love feedback! (or ideas for prompts/behaviors to try) https://art.heimdal.dev January 5, 2026 at 02:50AM

Show HN: Hover – IDE style hover documentation on any webpage https://ift.tt/NnG0ale

Show HN: Hover – IDE style hover documentation on any webpage I thought it would be interesting to have ID style hover docs outside the IDE. Hover is a Chrome extension that gives you IDE style hover tooltips on any webpage: documentation sites, ChatGPT, Claude, etc. How it works: - When a code block comes into view, the extension detects tokens and sends the code to an LLM (via OpenRouter or custom endpoint) - The LLM generates documentation for tokens worth documenting, which gets cached - On hover, the cached documentation is displayed instantly A few things I wanted to get right: - Website permissions are granular and use Chrome's permission system, so the extension only runs where you allow it - Custom endpoints let you skip OpenRouter entirely – if you're at a company with its own infra, you can point it at AWS Bedrock, Google AI Studio, or whatever you have Built with TypeScript, Vite, and the Chrome extension APIs. Coming to the Chrome Web Store soon. Would love feedback on the onboarding experience and general UX – there were a lot of design decisions I wasn't sure about. Happy to answer questions about the implementation. https://ift.tt/Wp84Rx3 January 5, 2026 at 01:43AM

Show HN: 3D Printed Difference Engine [video] https://ift.tt/Z6sevdo

Show HN: 3D Printed Difference Engine [video] https://www.youtube.com/watch?v=NvORut3h904 January 4, 2026 at 11:40PM

Saturday, January 3, 2026

Show HN: A New Year gift for Python devs–My self-healing project's DNA analyzer https://ift.tt/1n2vXO8

Show HN: A New Year gift for Python devs–My self-healing project's DNA analyzer I built a system that maps its own "DNA" using AST to enable self-healing capabilities. Instead of a standard release, I’ve hidden the core mapping engine inside a New Year gift file in the repo for those who like to explore code directly. It’s not just a script; it’s the architectural vision behind Ultra Meta. Check the HAPPY_NEW_YEAR.md file for the source https://ift.tt/7mCVSi2 January 4, 2026 at 02:20AM

Show HN: Turbo – Python Web Framework https://ift.tt/uXCrFLz

Show HN: Turbo – Python Web Framework https://ift.tt/XHxWIEZ January 4, 2026 at 12:15AM

Show HN: FP-pack – Functional pipelines in TypeScript without monads https://ift.tt/sve1bpH

Show HN: FP-pack – Functional pipelines in TypeScript without monads Hi HN, I built fp-pack, a small TypeScript functional utility library focused on pipe-first composition. The goal is to keep pipelines simple and readable, while still supporting early exits and side effects — without introducing monads like Option or Either. Most code uses plain pipe/pipeAsync. For the few cases that need early termination, fp-pack provides a SideEffect-based pipeline that short-circuits safely. I also wrote an “AI agent skills” document to help LLMs generate consistent fp-pack-style code. Feedback, criticism, or questions are very welcome. https://ift.tt/QZYWr4n January 3, 2026 at 10:00PM

Friday, January 2, 2026

Show HN: I mapped System Design concepts to AI Prompts to stop bad code https://ift.tt/XbNcIs8

Show HN: I mapped System Design concepts to AI Prompts to stop bad code https://ift.tt/AwW9dPy January 3, 2026 at 01:45AM

Show HN: CryDecoder – On-device ML for classifying baby cries (Swift, Core ML) https://ift.tt/nxq0pe1

Show HN: CryDecoder – On-device ML for classifying baby cries (Swift, Core ML) Hi HN, I’m the developer behind CryDecoder. I built this after too many nights at 3am staring at a crying infant, completely exhausted, trying to guess whether it was hunger, gas, or just general fussiness. I realized I was essentially running a mental decision tree on very little sleep, so I decided to see if I could automate some of that signal processing. What it does: CryDecoder analyzes short audio clips of a baby’s cry and classifies them into categories like hunger, discomfort/gas, tiredness, or general fussiness. How it works: • Tech: On-device audio feature extraction paired with a lightweight ML model trained on labeled cry patterns. • Performance: Inference runs locally on the phone, which keeps latency low and avoids sending audio off-device. Results come back quickly enough to feel near real-time. • Philosophy: This isn’t meant to replace parental judgment. It’s intended as an extra data point — a sanity check when you’re tired and not sure what to try next. The business side: The app currently uses a paid model with a preview. I’m an engineer first and still iterating on pricing and paywall placement. I’d appreciate feedback on: 1. The technical approach and responsiveness 2. Whether the paywall timing feels reasonable for a utility like this Thanks for taking a look. https://ift.tt/3aeSVNC January 2, 2026 at 11:56PM

Show HN: Text-to-3D Motion Generator (Hunyuan 1.0 wrapper) https://ift.tt/psu7hSO

Show HN: Text-to-3D Motion Generator (Hunyuan 1.0 wrapper) Hi everyone, I built a UI for the new open-source Hunyuan Motion model to generate 3D animations from text: https://hy-motion.ai It generates BVH files instantly. I'm trying to bridge the gap between "cool AI demo" and "useful game dev tool". Question for 3D devs/animators: If you were to use this in production, what is the single biggest missing feature? 1. Export Pipeline: Auto-conversion to FBX for Unity/Unreal? 2. Motion Fusion: Blending multiple prompts into one long sequence? 3. Rig Variety: Support for non-humanoid skeletons? Feedback is much appreciated. https://hy-motion.ai/ January 2, 2026 at 10:56PM

Show HN: Startboard – A simple little browser start page and bookmarks organizer https://ift.tt/tzAoqwD

Show HN: Startboard – A simple little browser start page and bookmarks organizer https://startboard.so/ January 2, 2026 at 11:26PM

Thursday, January 1, 2026

Show HN: Feature detection exploration in Lidar DEMs via differential decomp https://ift.tt/Tg8AvcY

Show HN: Feature detection exploration in Lidar DEMs via differential decomp I'm not a geospatial expert — I work in AI/ML. This started when I was exploring LiDAR data with agentic assitince and noticed that different signal decomposition methods revealed different terrain features. The core idea: if you systematically combine decomposition methods (Gaussian, bilateral, wavelet, morphological, etc.) with different upsampling techniques, each combination has characteristic "failure modes" that selectively preserve or eliminate certain features. The differences between outputs become feature-specific filters. The framework tests 25 decomposition × 19 upsampling methods across parameter ranges — about 40,000 combinations total. The visualization grid makes it easy to compare which methods work for what. Built in Cursor with Opus 4.5, NumPy, SciPy, scikit-image, PyWavelets, and OpenCV. Apache 2.0 licensed. I'd appreciate feedback from anyone who actually works with elevation data. What am I missing? What's obvious to practitioners that I wouldn't know? https://ift.tt/a6tQONd January 1, 2026 at 07:29AM

Show HN: DroidDock – Browse Android files on Mac with a Finder-like experience https://ift.tt/Vx92aEm

Show HN: DroidDock – Browse Android files on Mac with a Finder-like experience Show HN: DroidDock – Browse Android files on Mac with a Finder-like experience DroidDock is a macOS app that allows you to browse files on your Android device via ADB. Built with Tauri (Rust + React). Core features: - Browse files with Table, Grid, or Column views - Preview images/text without downloading (press Space) - Full keyboard navigation - Search, upload/download, multi-select - Dark mode support What's New in v0.2.x - File Previews : Press Space to preview images/text without downloading - Minimalist UI : Clean 95% grayscale design with better readability - Clickable Sorting : Click column headers (Name, Size, Date) to sort - Kind Column : Shows file types at a glance (Image, Video, Document, etc.) - Better Keyboard Navigation : Arrow keys in preview, Cmd shortcuts for everything Tech Details Built with Tauri (Rust backend) + React/TypeScript frontend. Rust handles all ADB communication for good performance. Small bundle (~15MB DMG universal binary), lower memory than Electron. Challenges 1. ADB Path Detection : Different package managers install ADB in different locations. Had to check 5+ common paths on startup. 2. Thumbnail Generation : Android doesn't expose a thumbnail API via ADB. I pull the first N bytes of image files and generate thumbnails on-the-fly with caching. 3. File Preview : ADB doesn't stream files – you have to pull the entire file. For large images, I had to implement chunked reading to check dimensions first. 4. Code Signing : Currently unsigned (requires $99/year Apple Developer membership). Users have to right-click → Open on first launch. Open Source & Free MIT licensed, no telemetry, no ads. Website: < https://rajivm1991.github.io/DroidDock/ > GitHub: < https://github.com/rajivm1991/DroidDock > Download: < https://github.com/rajivm1991/DroidDock/releases/latest > Would love feedback! This is my first Tauri app after years of Electron. The Rust learning curve was worth it. https://rajivm1991.github.io/DroidDock/releases/v0.2.1.html January 1, 2026 at 11:10PM