Show HN: The news in the last 30, 14, 7, 3, or 1 days https://bit.ly/3EFzyJ6

Show HN: The news in the last 30, 14, 7, 3, or 1 days I made this for when I come back from vacation and want to catch up on news. It's a bit of a simplistic LLM transformation on headlines and URLs that I store from RSS feeds. So it bugs out sometimes. But I think it might be useful to me. You can check out some of the prompts in the "debug" links. What do you think? https://bit.ly/4hFKV2a February 16, 2025 at 06:54AM

Show HN: Tech Brief – AI enhanced news reading https://bit.ly/3QjC768

Show HN: Tech Brief – AI enhanced news reading I built this because I wanted it, and I now use it every day. It's a simple news site that gathers and summarises tech content and discussions, across multiple sources, providing tight, easily digestable summaries along with some simple tooling to support reading workflows. 1) Hourly updated homepage with the latest tech news across the web. 2) A simple < 3 min "News of the Hour", every hour, audio clip. 3) Summaries of HackerNews and Product Hunt, incl. comments and sentiment (more to come). 3) GitHub login with AI summaries of any releases made to your starred repos. 4) Read/Unread article status. 5) Simple swipe interface and keyboard support. 6) Simple Bookmark/Readling List, and Favourite tags (logged in) No Tracking. Fast. Mobile Friendly. Easy sharing. https://tech.brief.page/ February 16, 2025 at 01:28AM

Show HN: Blunderchess.net – blunder for your opponent every five moves https://bit.ly/41h0Qy8

Show HN: Blunderchess.net – blunder for your opponent every five moves blunderchess.net is an open source, peer-to-peer chess app where every five moves, players each get to make one blunder-move for their opponent https://bit.ly/4hXSUaL February 16, 2025 at 01:22AM

Show HN: Letting LLMs Run a Debugger https://bit.ly/4b2Bpnp

Show HN: Letting LLMs Run a Debugger Hey HN, I just built an experimental VSCode extension called LLM Debugger. It’s a proof-of-concept that lets a large language model take charge of debugging. Instead of only looking at the static code, the LLM also gets to see the live runtime state—actual variable values, function calls, branch decisions, and more. The idea is to give it enough context to help diagnose issues faster and even generate synthetic data from running programs. Here’s what it does: * Active Debugging: It integrates with Node.js debug sessions to gather runtime info (like variable states and stack traces). * Automated Breakpoints: It automatically sets and manages breakpoints based on both code analysis and LLM suggestions. * LLM Guidance: With live debugging context, the LLM can suggest actions like stepping through code or adjusting breakpoints in real time. I built this out of curiosity to see if combining static code with runtime data could help LLMs solve bugs more effectively. It’s rough around the edges and definitely not production-ready I’m not planning on maintaining it further. But I thought it was a fun experiment and wanted to share it with you all. Check out the attached video demo to see it in action. Would love to hear your thoughts and any feedback you might have! Cheers. https://bit.ly/3EAtLVg February 12, 2025 at 10:54AM

Show HN: Lightweight and robust CLI color converting utility https://bit.ly/4hF9Xi0

Show HN: Lightweight and robust CLI color converting utility I started this project because I found myself converting between Hex and RGB a lot. As I was frequently visiting various color picker websites, I began thinking more and more about how color conversions even work in the first place. What is a color space? Using any random color-picker online to go from RBG<->Hex works plenty fine, but, I think CLI tools are cool. I'm still pretty new to the Linux scene, and I really enjoy finding random command line programs to play with. I searched around a bit on Github and the AUR and couldn't find any CLI color conversion utilities, which I honestly found surprising (maybe I didn't look hard enough). I decided I'd really enjoy trying to make a simple command line program for RGB<->Hex, and the scope slowly expanded. I could see myself expanding it (maybe including more color formats, suggesting complementary colors) but for now, unless people discover ways to break it or offer any pull requests, I think I'll be moving on to other projects. It has no dependencies besides Python, and can be easily installed on mac/linux (see the README for more). I'm not certain how you'd set it up as a command line program on Windows, but you can just use Python in cmd to use the script anyway! https://bit.ly/4gKzwgr February 15, 2025 at 12:31AM

Show HN: VimLM – A Local, Offline Coding Assistant for Vim https://bit.ly/4jZQ3zF

Show HN: VimLM – A Local, Offline Coding Assistant for Vim VimLM is a local, offline coding assistant for Vim. It’s like Copilot but runs entirely on your machine—no APIs, no tracking, no cloud. - Deep Context: Understands your codebase (current file, selections, references). - Conversational: Iterate with follow-ups like "Add error handling". - Vim-Native: Keybindings like `Ctrl-l` for prompts, `Ctrl-p` to replace code. - Inline Commands: `!include` files, `!deploy` code, `!continue` long responses. Perfect for privacy-conscious devs or air-gapped environments. Try it: ``` pip install vimlm vimlm ``` [GitHub]( https://bit.ly/4i0lEzs ) https://bit.ly/4i0lEzs February 15, 2025 at 12:34AM

Show HN: I made a tiny book using a pen-plotter and AI https://bit.ly/41eoRpF

Show HN: I made a tiny book using a pen-plotter and AI Hey HN, I want to share a personal project: I made a tiny pen-plotted book for my wife. I did everything myself—drawings (with some help from Midjourney), plotting, cutting, and binding. I even used a 3D printer to make a helper tool. It's absolutely over-engineered, but I enjoyed it a lot. Multi-disciplinary projects, especially those with a physical output, are a lot of fun for me. The post covers the process in detail, but if you're interested in anything specific, let me know. Cheers! https://bit.ly/4gIVFLQ February 10, 2025 at 06:52PM

Show HN: HackerVoice – An Experimental AI Podcast Covering Hacker News https://bit.ly/4hOowQ2

Show HN: HackerVoice – An Experimental AI Podcast Covering Hacker News Hey HN: What it does: HackerVoice automatically generates a daily podcast summarizing the top five trending Hacker News topics using AI. How it works: Uses a combination of Gemini and GPT-4o to analyze and summarize trending topics. Leverages OpenAI’s text-to-speech (TTS) engine to generate natural-sounding narration. Runs on an automated schedule (cron job at 16:00 UTC daily). Episodes are available for listening at: https://bit.ly/4hXtXvQ . https://bit.ly/4hXtXvQ February 14, 2025 at 01:35AM

Show HN: Dockershrink – AI Assistant to reduce the size of Docker images https://bit.ly/4gEY8XR

Show HN: Dockershrink – AI Assistant to reduce the size of Docker images For the past few months, I've been hacking around a project I call Dockershrink. It automates a simple task: Take a Dockerfile and optimize its code with the goal of reducing the size of the final Docker image. People don't realize that we can apply some very basic techniques to reduce, for eg, a 2GB image down to just ~100MB: - Multistage builds with light-weight base image for final stage - Remove unused dependencies - Optimizations specific to the tech stack And I feel like I've already done this optimization for my personal projects and backend apps at my job(s) a couple of times. The project currently uses GPT-4o (open source so you can run it locally) and only works for Nodejs projects. There are a couple of reasons why I think dockershrink can be better than using just Vanilla LLM or Github Copilot/Cursor: - Image optimization can benefit from a lot of custom prompting, especially when you have insights about specific tech stacks. Describing techniques deeply in the prompt gave better results than simply asking the LLM to "optimize code for bloat reduction". - A RAG approach will be truly beneficial. I plan on giving dockershrink access to up-to-date documentations of Docker, Bash and all programming languages out there. Additionally, it can be given a few suitable chunks of code to enhance the context. - Analysing custom base images: most orgs have their customized base images. Adding context about these can further help Dockershrink make better decisions. Try it out - "brew install dockershrink" Happy to hear your thoughts! https://bit.ly/4b3seTQ February 13, 2025 at 11:45PM

Show HN: Minimalist black and white drawing generator https://bit.ly/41gjmqF

Show HN: Minimalist black and white drawing generator https://bit.ly/4hzaceB February 13, 2025 at 03:55PM

Show HN: RAG Engine – Connect external data to LLM in minutes https://bit.ly/4gAw2Nf

Show HN: RAG Engine – Connect external data to LLM in minutes https://bit.ly/4k8jLCW February 13, 2025 at 03:15PM

Show HN: Make Easy Async Rust (Mea), runtime-agnostic primitives https://bit.ly/3EzsayS

Show HN: Make Easy Async Rust (Mea), runtime-agnostic primitives https://bit.ly/4hxvg5a February 13, 2025 at 01:49AM

Show HN: Auto rename downloads by AI and with your own naming rules https://bit.ly/42TpFkZ

Show HN: Auto rename downloads by AI and with your own naming rules Hii HN! We've built a Chrome extension called Cantrips.ai that auto generates meaningful filenames for pdf, txt, and docs downloads. It has tailored formats for major file types like papers, books, financial reports, etc. For example, a paper is always formatted as download date - title - first author's last name - area, so the filename would be 20250208 - Attention Is All You Need - Vaswani - LLM instead of 1706.03762 from arXiv. We are also developing a feature where users can add or adjust their file naming preferences. For example, if you like underscores and download meeting memos a lot, you can add meeting memos = interviewee's name_company_position_topic_date. The reason to build this extension is that my desktop is buried with meaningless and odd filenames, so I often can't find which is the one I want. I have to go to that website and download it again, sometimes the repetition number amounting over (10). More importantly, I desperately want my desktop/finder to look tidy. It feels great when everything is organized, but I don't want to handle the renaming in the mid of my research (and I become a bit lazy later :< Note that the extension hasn't supported downloads from some websites like Github due to technical complications. As a first-time dev, I just realized even a small tool can take much time... but we assume a similar preference feature can be applied to other productivity tools like folder organization or website bookmarks. Happy to get suggestions and learn if you really need such tools. If you want to try the extension, here's the link: https://chromewebstore.google.com/detail/cantripsai-auto-ren... https://chromewebstore.google.com/detail/cantripsai-auto-rename-do/fnaemmlnchphilapbdjejjlhoomcpblk February 12, 2025 at 11:48PM

Show HN: I Applied to Y Combinator for the 3rd Time in a Row https://bit.ly/3WZV1mb

Show HN: I Applied to Y Combinator for the 3rd Time in a Row Join Open Community on Discord: https://bit.ly/3CKrMgu Follow on LinkedIn: https://bit.ly/4hUjd1n Follow me: https://bit.ly/4gKWiow https://www.youtube.com/watch?v=5gBU_MK5fqE February 12, 2025 at 06:18AM

Show HN: A lightweight and flexible open source bastion https://bit.ly/4huXpK3

Show HN: A lightweight and flexible open source bastion OneTerm is a simple, lightweight and flexible enterprise-class bastion host, designed and developed based on 4A compliant, i.e. Authen, Authorize, Account, and Audit, which ensures the security and compliance of the system through strict access control and monitoring features. https://bit.ly/4jN04Ae February 12, 2025 at 03:08AM

Show HN: HypeBridge – Your Dedicated AI-Agent Driven Influencer Marketing Agency https://bit.ly/4gxTivj

Show HN: HypeBridge – Your Dedicated AI-Agent Driven Influencer Marketing Agency https://bit.ly/4gB77cE February 11, 2025 at 10:02PM

Show HN: Wordle Charts – insights about Wordle you don't need https://bit.ly/3EHwFr2

Show HN: Wordle Charts – insights about Wordle you don't need Hello HN! I'm a big fan of Wordle and I originally got this idea from seeing people gripe about Wordle suddenly being "harder" than usual. Wondering if this was true, I set out to snoop around the NYT's publicly available data, which gave me some pretty cool insights. I've put some of them on this simple site made with React and Claude. There's a grand total of 7 visualizations, with some fun little touches here and there. My favorite is probably "Clairvoyant Guesses," which shows some (to put it nicely) suspicious day-to-day guessing patterns. There's also a fun little easter egg when you type "cat" and then enter a word into the "Find Word:" box. Let me know if you have any suggestions, and any feedback at all :) Github Repo: https://bit.ly/3EzdeAT... https://bit.ly/4gEQKvs February 7, 2025 at 06:45PM

Show HN: WhisperCat – An Audio Recorder and Transcription Tool https://bit.ly/4aR9nv3

Show HN: WhisperCat – An Audio Recorder and Transcription Tool Hi HN, I wanted to share my first open-source project with you all: WhisperCat . WhisperCat is a small desktop application for recording audio and transcribing it using OpenAI's Whisper API. I built this because I needed something simple and reliable for my own transcription workflows, and now I'm hoping it might be useful to others as well. It's still pretty early stage, but it works well for basic audio recording and transcription tasks. What It Does: Lets you record audio with your preferred microphone. Transcribes audio files automatically via Whisper (OpenAI's transcription API). Supports global hotkeys for recording (e.g., CTRL + R or a custom sequence like triple ALT). Runs in the background (system tray) when minimized. Has a basic microphone testing feature to help you pick the right device. Shows desktop notifications for events (e.g., when recording starts or errors happen). Platforms: WhisperCat is available for Windows and Linux , and there’s also an experimental macOS build you can try if you’re feeling adventurous: Experimental macOS Build You can download the latest release here: https://bit.ly/4jQy2E6 Feedback is welcome! https://bit.ly/4aTxqJD February 10, 2025 at 08:41PM

Show HN: Small back end server to render PNG from VueJS widgets https://bit.ly/4aXyxrN

Show HN: Small back end server to render PNG from VueJS widgets In my company we need to send Discord or WhatsApp messages (eg. alert about something, etc), which cannot unfortunately embed HTML widgets, but I wanted to make it possible to show a "card-like" component with colors, graphs, etc I coded a small backend which lets you mount a VueJS widget (it would work with React too), pass it props from the POST/GET parameters, render it to PNG and send it back You can see an example here: https://bit.ly/4hwLGdW https://bit.ly/3EqJrtW February 10, 2025 at 08:24AM

Show HN: Infinite Horizontal Array of Text Editors https://bit.ly/4huGMxU

Show HN: Infinite Horizontal Array of Text Editors I made this app to write books chapter by chapter, while taking & browsing through temporary notes for each chapter. The leftmost sidebar is the list of chapters. The sidebar to the right of that is the list of editors in the current chapter. The UI & UX are a bit weird, but they have a basic logic to them. https://bit.ly/4hvV7u5 February 10, 2025 at 02:25AM