Show HN: Ente Authenticator – open-source 2FA app with e2ee backups https://ift.tt/I1wgSsX April 30, 2023 at 07:14PM
Show HN: ArchitectGPT – AI Powered Home Design Too Hello everyone, I'm excited to share with you my new app, ArchitectGPT! With ArchitectGPT, you can upload or take pictures of any residence/home and transform it using AI via text or pre-selected themes. Whether you want to experiment with different color schemes, furniture arrangements, or even add new rooms to your home, ArchitectGPT can help you visualize the possibilities in seconds. The app uses state-of-the-art machine learning algorithms to generate realistic and personalized design recommendations based on your preferences and needs. ArchitectGPT is perfect for anyone who wants to explore home design ideas without the hassle and cost of hiring a professional designer. It's also great for architects, interior designers, and real estate agents who want to quickly create virtual staging for their clients. The app is easy to use and doesn't require any design skills. Simply upload a photo of your home, select a theme or provide a description of what you want to achieve, and let ArchitectGPT do the rest. You can save your favorite designs and share them with your friends and family. https://ift.tt/YNq9aGJ April 30, 2023 at 03:24AM
Show HN: Open-Source Implementation of John Conway's Mathy Game of Hackenbush Hackenbush is a fascinating game that led to leaping developments in combinatorial game theory. It caused the discovery of the surreal numbers - an absolutely, incredibly, tremendously large field of numbers. To help it find more popularity, I made an open-source version, mainly for mobile platforms. https://ift.tt/cFVqLGz April 30, 2023 at 11:41AM
Show HN: A Gentle Introduction to the Fediverse There's a lot of great explainer sites and articles about the fediverse, but I wanted to make something that serves as a quick introduction for a more casual audience, and lets you dig deeper from there. https://ift.tt/xnZh4Hp April 29, 2023 at 09:36PM
Show HN: I made a tool to easily credit co-contributors in Git commits Hi Everyone! The motivation behind creating this tool is to provide an easy way to give credit to contributors in various situations: - In open-source projects, when a pull request (PR) is closed without merging but the idea or code is later implemented. - During pair programming sessions, where two or more developers work together on a single commit. Existing solutions were either too complicated or didn't work as expected, so Git Add Co-Author was developed as a simple, easy-to-use alternative. https://ift.tt/586WZVP April 29, 2023 at 03:17AM
Show HN: Jarvis AI – Text, iMessage, and Email ChatGPT We're back with another ShowHN! When we launched, you could text Jarvis AI using regular SMS messages from your phone. Since launching 3 weeks ago[1], we've introduced two new channels for using ChatGPT. Now you can use ChatGPT over SMS text message, iMessage for Apple-enabled devices, and via Email. It is super interesting to forward an email to Jarvis AI and see its thoughts on your email thread. It can help you brainstorm or it can suggest a reply to previous emails. 10 messages free forever, more volume is free over iMessage and Email for a limited time (until the HN hug of death!). You don't have to sign up or anything to try it. Just send a text to: +1 (855) 676-1two89. Thanks for checking this out. Many exciting features are coming soon to make this more than just a different interface to ChatGPT. We want to make AI accessible to more people, over more channels, with more useful things for your day-to-day. For medical professionals, we added the /diagnose command. Ask Jarvis "/diagnose 32 year old harsh cough" for example. Soon, we are adding features like /invoice for generating invoices and /remember for notes and reminders. [1] Related: See the first HN post when we launched here: https://ift.tt/lfyIcYM https://jarvis.tel April 28, 2023 at 06:06PM
Show HN: Code-Narrator: Automating Documentation with GPT-4 As a solo developer on a sizeable project, I found myself facing the challenge of creating documentation, a task I admittedly do not enjoy. Fortunately, ChatGPT arrived just in time. After experimenting with it, I discovered that it generates high-quality documentation for code files, even better than what I could produce manually. This realization led me to develop Code-Narrator, a client that simplifies the documentation process. Code-Narrator ( https://ift.tt/aZUCmV9 ) utilizes GPT-4 to analyze your code files and automatically generate documentation. The tool is language-agnostic and has been tested with TypeScript, GraphQL, Solidity, C#, Kotlin, and more. As long as the files are in plain text, Code-Narrator should work seamlessly. The primary goal of Code-Narrator is to ease the documentation process for developers, transforming them from writers to editors. While developers are still responsible for verifying the accuracy of the generated documentation, the initial writing is handled by the AI. If GPT-4 produces incorrect documentation, it typically indicates that the code needs clarification, or a brief comment should be added to guide the AI. A general rule of thumb is that if GPT-4 cannot comprehend the code, it may be too complex for the next developer. However, Code-Narrator is constrained by GPT-4's 8192-token limit, which can be problematic for extensive code files. Those with access to the gpt-4-32k variant should expect better results. Upon its first run, Code-Narrator creates a configuration file by analyzing your project, and then prompts you to review it for accuracy. The key configuration aspects include the "include," "config_files," and "source_path" settings. In its second run, Code-Narrator generates documentation for your entire project. The process is time-consuming, taking approximately 45 minutes to complete from scratch. However, the tool is: - Flexible, allowing for the creation of custom pages such as How-To guides, tutorials, FAQs, READMEs, and other bespoke content. - Multilingual, supporting 25+ languages (as many as GPT-4 supports). - Versatile, capable of generating documentation in various formats (LaTeX, HTML, with the default being Markdown). For a demonstration on transforming a few lines into a How-To guide, watch this video: https://www.youtube.com/watch?v=uJtVCUOTkvw . Remember that brevity is key, as the more concise the input, the more GPT-4 can contribute. Code-Narrator also supports custom plugins, with tutorials available at https://ift.tt/o3ZTX9p... . In terms of size and cost, Code-Narrator consists of 45 files and 1712 lines of code. The total cost of generating documentation for the entire project is approximately $2.5, a significant savings compared to manual documentation. During the development of Code-Narrator, I noticed several benefits: - Improved function naming: Reading the generated documentation led me to revise vague or overly general function names, resulting in better code and documentation. - Concise input: Focusing on reducing the size of the input file (liquid) became a fun challenge, helping to optimize the process. - Enjoyable interaction: Working with ChatGPT proved more enjoyable than manually writing documentation, and the more I experimented, the better the results. - Minimal input for tutorials: I was pleasantly surprised by how little input was required to create How-To guides and tutorials using GPT-4. - Encouragement to refactor: The 8K token limitation may be restrictive, but it also encourages developers to refactor their code for improved readability and structure. As a prototype and proof of concept, Code-Narrator has some limitations. I'm excited to see where Code-Narrator goes from here, and your feedback is invaluable. Thank you for taking the time to explore this project! https://ift.tt/aZUCmV9 April 28, 2023 at 03:49PM
Show HN: ScrapScript – A tiny functional language for sharable software Hi friends, I started casually working on scrapscript in 2015. I built a few compilers over the years to test out various ideas/implementations, and I think I'm finally happy with the overall design. The code is not public yet. Email me at hello@taylor.town if you're interested in joining the core team later this year. Let me know if you have any questions or feedback :) https://scrapscript.org April 26, 2023 at 05:15PM
Show HN: A Bel compiler to Emacs Lisp bytecode In his classic Lisp in Small Pieces, Christian Queinnec actually suggested this project: compiling Scheme to Emacs Lisp byte code. I took up the challenge with Bel instead of Scheme. Much of the code actually comes from the book but adapted to the problem at hand. https://ift.tt/EH8b2L6 April 28, 2023 at 01:23AM
Show HN: Web app turns your text into p5js (graphics) code using GPT Text → GPT → p5 | An app that turns your text prompt into p5js code (computer graphics) using OpenAI's GPT and displays it. Under the hood: Nextjs, React, CodeMirror, p5js I got into programming through arduino and processing. I've always thought about how to lower the barriers for people to start programming. With GPT, we can now turn plain text into code, allowing people to start coding without knowing code. OpenAI APIs don't come cheap! If you like the project, consider sponsoring access for others here: https://ift.tt/6uCaFR0 Cheers! https://ift.tt/fegolQy April 27, 2023 at 08:58AM
Show HN: Chrome Extension Automatically Highlights Flawed Reasoning on Twitter Working on a chrome extension that can catch logically fallacious tweets. Wanted to know if this is something that would be useful to anyone? Plan is to make it as free as possible. I am not making any money from this. But since it is using GPT-3.5, there is an OpenAI API fee of $0.0002 / about 750 words that is scanned on Twitter. See fallacy.review/pricing for more info on that. Would love feedback. https://fallacy.review April 27, 2023 at 07:11AM
Show HN: Retro games hosted in Cloudflare Pages for free Created some free sites to play online versions of retro MS games like Minesweeper, Solitaire and others such as Sudoku & Tic Tac Toe. I learned about Cloudflare's Pages at same time to host all the code at no cost. https://retrogmz.com/ April 27, 2023 at 12:18AM
Show HN: Use ChatGPT on a 2 Dimensional Interface I build ChatGPT-2D with the idea to enable people to branch AI conversations interactively, pose contextual questions based on AI response and visualize your entire dialogue on a 2 dimensional map interface. What do you think? https://ift.tt/p3uTL2Y April 26, 2023 at 07:56AM
Show HN: Ordently – Consciously plan your day and your life I've been using a task management tool for the past 1 year that I built. A few months ago, I spent some time to make it more generic because my partner wanted to use it as well and she's been loving it ever since. Love her, but she's a bit biased. Firstly, this is a todo app for your life. Existing tools are built around how we work as employees in a company. With a company, all the habits, goals, vision and rituals are given to you in an employee handbook. The company is our coach, and in most cases, we listen and do as the coach says. Its easier to get things done in this environment. In our personal lives, we gotta figure out our goals, work on our habits and setup rituals. We're also more flexible, more forgiving on when we want to do certain things and more rigid on the others. The Daily Planner is central to that ideology, working with one off and repeatable tasks . You onboard with your day first, could be as simple as calling your mum or going on a walk or do yoga. As you get more comfortable, you start to consciously build a life that you want to live by creating rituals and setting goals as you get more confident. Personally, I haven't been able to get that through Todoist or Notion. https://ift.tt/yMYs3kT April 26, 2023 at 02:51AM
Show HN: A C++ web/application framework I have been building for the last 12yrs Back then there were not a lot of frameworks for C++ like there are available now, gradually added serialization, reflection, orm, modules for apache|nginx, then started adding programming language integration and then finally added support for building on various Os'es and also support for most of the build tools out there. https://ift.tt/Hn3YLXK April 24, 2023 at 06:47PM
Show HN: I quit my job to build a Kubernetes GUI with Rust About a year ago I was working on a project with mirrored Kubernetes clusters deployed across various regions. Constantly switching contexts was a big pain for me and I badly needed something more practical to work with multiple clusters, ideally simultaneously. At that time everyone was talking about Rust and I really wanted to try it out. I then found Tauri, a framework to build GUI apps with Rust + JavaScript. I was sold. I learned Rust and built the app I always wanted to use. Fast, lightweight and with the ability to connect to multiple clusters simultaneously. Fast forward to today, there’s a few thousand users and I’ve quit my job to go all in on this product. Would love to get you to try the app and share your feedback. It would mean a lot to me! Thanks! https://aptakube.com April 24, 2023 at 06:40PM
Show HN: Q&A Bot talking in Hinglish about PDFs Such an amazing time to build applications that can actually make a difference in everyday lives! We've built a simple Q&A bot that can answer your questions in 𝐇𝐢𝐧𝐠𝐥𝐢𝐬𝐡 about any pdfs, wrapped it with a simple command 𝐥𝐜-𝐬𝐞𝐫𝐯𝐞 𝐝𝐞𝐩𝐥𝐨𝐲 𝐩𝐝𝐟_𝐪𝐧𝐚, your bot is now ready to be part of your application stack, I've uploaded a demo where I talk to the bot in half-hindi & half-english about an insurance document - https://twitter.com/_deepankarm_/status/1650447522111029248 https://ift.tt/9SatwAb April 24, 2023 at 04:07PM
Show HN: I made a website for letter writing and slow communication After struggling to keep in touch with a friend who moved away to Japan, I set out to build something that enabled deep conversations without the pressure and required scheduling of instant messaging https://ift.tt/5Z80XGt April 22, 2023 at 10:24PM
Show HN: I'm building a Strava alternative without all the social media crap I'm working on https://cubetrek.com , a web app to manage, visualize and compare your running, hiking, mountainbiking, skiing... activities. Some features include: a github-style calendar heatmap, 3D visualization of tracks (especially useful for hill climbs and mountaineous terrain in general), a world map displaying all your activities at once. Excluded features: although you can share yoir tracks to the world, should you choose so, there are no friends, no likes, no comments, i.e. none of that social networking stuff. And no ads. Any feedback is appreciated, let me know what you think, what to improve! https://cubetrek.com April 23, 2023 at 03:23AM
Show HN: Stadai – Your virtual study buddy powered by ChatGPT With Stadai, you can create customized quizzes and flashcards on any topic from your own study materials or class notes. Stadai is a chat-based study platform that offers a personalized learning experience. You can also access auto-generated quizzes and flashcards on important topics to enhance your learning experience. Stadai saves your progress and stats, helping you track your learning journey, monitor your performance, identify areas for improvement, and optimize your study strategy. Stadai is perfect for students, professionals, and anyone who wants to boost their learning and knowledge retention. Whether you're preparing for exams, learning new skills, or exploring new interests, Stadai can help you achieve your goals. Try it out now at: https://www.stadai.com/ Please share your feedback on Stadai in the comments below, we would love to hear from you! Thank you! https://www.stadai.com/ April 22, 2023 at 12:22AM
Show HN: ChatGPT-powered Search Bar for your Site Built a small free widget that is a ChatGPT-powered search bar for your site. You can use it on your blog, guides, docs, and resources pages. It crawls and indexes your site and then answers search queries with questions using your site content as a source. It even references the source material so visitors can dig deeper. It also has memory so you can have repeat searches just like ChatGPT. Built with Langchain, Pinecone, and OpenAI. https://ift.tt/ib7QYTp April 21, 2023 at 11:13PM
Show HN: GPT powered prompt-to-storyboard with Coqui voices, StabilityAI images I had 2 weeks off from work and wanted a pet project before heading back. With GPT and Generative AI in the news, I decided to chain multiple Al products together to build something really cool. I set my end goal to be: prompt-to-storyboard (aka fun videos generated purely via generative AI). There exists some prompt-to-video products, but I wanted to tell stories with audio as well. The end product takes an initial prompt and produces a series of images and audio files, which I then combine (with subtitles) into the final video. To showcase videos, there is a basic upvote/downvote leaderboard. Text | OpenAI https://openai.com/ Text is generated in a few high-level steps that I ask GPT to work through. These are all based on the initial user prompt, as such (ideally) indirectly controlled by the user. - Create a concept for a movie scene based on the prompt, including the theme and setting - Define each character in the scene - Define how each character looks - Define how each character sounds - Define 'frames' of the storyboard All of this textual information is defined in a JSON object I describe to GPT. I then take GPT's output and build the storyboard with the tools below. Voices | Coqui https://coqui.ai/ From the GPT output, I needed three major pieces of information to build voices in a way that I found satisfying: - Description of the voice - Description of the performance - Text of the actual dialog spoken Coqui has a product called 'prompt-to-voice', where you can describe how a character will sound and a custom voice is made for that character - this is how GPT defines the characters to use in the storyboard. As such, every voice is unique per storyboard. GPT will decide that a certain character is an "older man with a raspy voice", and I'll ask Coqui for that type of voice. In addition to this, in order to describe the performance, GPT outputs a basic emotion to summarize the line of dialog (happy, sad, angry, etc) - this is also sent to Coqui per audio clip generated. Images | Stability AI https://stability.ai/ While I originally setup the storyboard generator to use DALL-E due to already integrating with OpenAl for GPI, I found the cost prohibitive. As such, the images generated for the storyboards are from Stability Al's Stable Diffusion (stable-diffusion-512-v2-1). I combine the description of the frame that GPT provides, in addition to the theme and setting that GPT output for the whole storyboard, to generate each frame. Since GPT controls the data sent to Stable Diffusion with the description of the frame as well as the theme and setting, if your prompt dictates a theme it should hopefully translate into a theme in your storyboard. Both the storyboard and the 'prompt enhanced' image generation in the 'Create Content' tab pre-feed a GPT request with a summary of Stability Al's prompt guide. It will try and pick keyword weights to improve the image, and much like the setting and theme, keywords should be influenced by the initial prompt provided to the product. Conclusion Have fun and make my 2 weeks of work seem worth it! Voting on storyboards and creating storyboards both require a simple Google login to get access. https://meyer.id April 21, 2023 at 05:35AM
Show HN: Create your own full-featured VPN server We think VPN providers encrypt our data and increase our security and it is true but there is a problem: we have to share our data with them instead of ISPs. AdminVPN is a side project that allows ordinary people to create their own VPN server. PS: This is my first post here, your feedback is really appreciated! https://adminvpn.co/ April 20, 2023 at 10:18PM
Show HN: Mage, Unlimited 50 Top AI Text-to-Image and GIF Models Hi Hackernews! Mage is the incredibly simple and fun platform with over 50+ top, custom Text-to-Image AI models as well as Text-to-GIF for all to create with their imagination, unlimited & unfiltered. Start with fast and unlimited Stable Diffusion for free! The first Mage link posted ever was here on HackerNews back in September with the promise of Free, Fast, & Unfiltered Stable Diffusion. Turns out, avoiding the h*ll of pip installs and CUDA errors while enjoying this incredible tech was (and is) a popular idea! Since then, we've grown into an incredible community, with a lively Discord and 1M+ monthly active users on the site. We've added explore, profiles, history, social, and 50+ of the best fine-tuned models to boot. And today, we're live on Product Hunt! Would love to hear your thoughts and feedback as we continue to grow and evolve. Eternally grateful that HN was the launchpad that started everything for us! https://www.mage.space April 21, 2023 at 02:18AM
Show HN: InsightFlow Hey everyone, sharing InsightFlow, a (long) weekend project I made using GPT4. I am bit anxious sharing it since I barely knew how to code in Python before but I was simply amazed on how much GPT was able to help me write something that actually works (I hope). My goal was to create a library that empowers people to ask questions from their data, regardless of its source. InsightFlow does just that, it has some modules that allow s parsing information existing in (for now) video (its audio part), html, and in general text and provides a chat interface on top. I would love to expand this to image and eventually video parsing. I know there are some companies that aim for the same but I could not find an opensouce alternative for it. I tried making it modular so different modalities can be added later on. https://ift.tt/wu8O3t6 April 20, 2023 at 06:22PM
Show HN: ChatGPT to control your own app (text-to-action library) ActionIt is a text-to-action library built to make it easier to perform actions based on natural language input. It opens the way for applications that don't only retrieve information but actually interact with functions, extracting necessary parameters or asking follow-up questions where necessary. In simple terms, your functions are presented to ChatGPT and the correct one is chosen and executed based on a natural language input. Would love any feedback or feature requests:) https://ift.tt/EzoHV2v April 20, 2023 at 03:34AM
Show HN: A deterministic update to my tough-as-nails 2D unity mobile game Hello HN! I don't often see a lot of game dev content on hacker news, so I thought it would be fun to add some! I just spent the last 5 months updating my mobile game Command Center Earth to version 2.0.0. The trailer on the website posted is a culmination of all that work! The funny part is that while the "Fully Deterministic" refactor made to the game only gets a small callout in the trailer, it's what took the majority of the time! I could have never possibly imagined how much time, energy and testing it would take to get the game reproducibly deterministic with Unity! And even with all that work, I can't 100% guarantee that it is deterministic across all devices (although my testing shows things hold together on all devices I've tested). All things considered though, I'm very happy with how things came together! In addition to the deterministic refactor, I added 3 new levels to the game, 2 of which were only possible as a result of the refactor! Without it, all the bumping of those meteors (on Haxer & Frank) would have produced a different level scenario on each retry! Additionally, having things deterministic means that my leaderboard is now accurate to 0.01 seconds! There were some big visual overhauls as well, but I thought the HN community might be the most intrigued by the determinism updates! Thanks for checking out my game! P.S. I plan on writing a blog post on all that I've learned, in the hopes that the next developer to come along has a better go of it than I did btw. https://ift.tt/5L4oiN0 April 20, 2023 at 12:45AM
Show HN: GoGoBrowse – A Peer to Peer Web Browser Hi HN! GoGoBrowse is a side project I've been working on that allows 2 users to browse the web together while voice chatting. It's a proof of concept for a new model of browsing the web I've been thinking about. My thought is that before a leap to a 3D Metaverse, we need a 2D Metaverse, which is simply social web browsing. I wrote more about it here: https://ift.tt/Xg64ajw... Though the goal of an entirely social web browser is still quite a ways off, I think of this as a small first step in that direction. I'd love any feedback on the app itself, and the general concept of social web browsing. https://gogobrowse.com April 19, 2023 at 11:50PM
Show HN: Enlinko – link two words using related words based on word2vec Hello, This game uses idea of semantic similarity (called relatedness in my game), like in Semantle and Contexto. But i had different idea for gameplay - instead of guessing secret word, i wanted to make a game where goal is to link two unrelated words. It can be done by placing related words between starting and ending words. In my game there are endless ways to solve same puzzle. There's plenty of room for experiments. I've used semantic vectors from this model: https://ift.tt/580MZG2 https://enlinko.com/ April 19, 2023 at 10:22PM
Show HN: Database for analyzing US companies, visualize using Apache SuperSet My main motivation was that I wanted to be able to drill down and filter across all the available stocks, look at the data for myself, and narrow down on the stocks I am interested based on my own sets of criteria, and make data-driven analysis for my personal investment strategies. I used PostgreSQL as the backend database for ELT data pipelines, and used Citus Data cstore_fdw for columnar compression for the final dataset. All financial data is coming from SEC Edgar, https://ift.tt/mkXNo3H . I used Python for downloading most of the data. I also run the data load development locally on my home Ubuntu server that I built 5 years ago. I bought 4TB of M2 disks for best database performance, with PRIME B360M-A motherboard and Intel Chip Coffee Lake S. I built the website simply using WordPress, and I run Apache Superset using gunicorn via Apache Webserver reverse proxy. The registration form I had to build myself with PHP and some JavaScript, because it needed to automatically create a SuperSet user upon registration. Otherwise, I would need to input everyone manually. I used Python again for the data integration. Please don't use the database directly as an investment tool, as its in Beta, and the data still needs to undergo heavy data quality checks, please confirm all the numbers yourself, as I provide a link for every company to the SEC filings. https://ift.tt/BvA4HIw April 19, 2023 at 02:46AM
Show HN: AI Playground by Vercel Labs Hey, Jared Palmer (creator of this playground) here. Really excited to ship this. I’ve been building this over the past few weeks to compare LLMs from different providers like OpenAI, Anthropic, Cohere, etc. At Vercel, I manage our Frameworks division (including Next.js, Svelte, and Turbo) and wanted to also dogfood some of the latest features in a slightly larger application. This playground takes a lot of inspiration from https://nat.dev and is built on Tailwind, ui.shadcn.com, and some upcoming Vercel products we’re announcing soon. We’re going to continue adding models to compare and add other frameworks to generate code snippets from. https://play.vercel.ai April 19, 2023 at 04:08AM
Show HN: Offsuit – Casual Poker, Redesigned For the past year my friend and I have been building a dead simple offline poker app that we actually wanted to spend time in. No constant pop-ups. No account needed. No waiting for tables. No fake felt or neon. Just free poker against intelligent AI opponents with helpful in-game stats. We’ve started offline, but are working towards online-multiplayer, tutorials for new players, and more in-game stats. Would love your feedback! https://offsuit.app/ April 18, 2023 at 07:37PM
Show HN: Quorbo – a quick and quirky quest for the quote Hey HN, Today I'm launching Quorbo (www.quorbo.com): a simple letter-revealing game (think Wheel of Fortune with some twists) where you get 6 turns to guess the day's quote! It's my first post-parenthood side project and first web game. Being a working dad has caused me (for the first time, believe it or not) to focus on simplicity. Up until about a year ago, endless free time secretly plagued me... because I love _building_, and more free time meant: more room to add complexity. Not anymore! Quorbo is the first of my initial batch of three simple word games, and I can't wait to make more. Let me know what you think! (improvements, bugs / quirky behavior / stumbling blocks, any and all feedback welcome!) Enjoy! https://quorbo.com April 18, 2023 at 03:16AM
Show HN: Instant AI Powered Support Create a virtual assistant for your product with a single click 1. Tell us your website 2. Choose the pages you'd like Bubbly to learn from 3. We will instantly create a GPT3 AI Bot that can answer any question about your product or service. https://ift.tt/VEqJyUO April 18, 2023 at 01:43AM
Show HN: Magic Happens – let ChatGPT manage your Kubernetes cluster I built this kubernetes operator as a proof of concept this weekend.. It only has a single required item in the spec, a freeform description field. The operator will use chatgpt to generate a spec, then immediately apply it to the cluster. It makes some attempt to correct errors if there's a problem with the syntax. It will leave additional comments, questions or instructions in the status field of the object. I built this in a weekend and it's still quite unrefined. It's in no way production ready, please don't use it for anything real, but it works better than you would think, considering how simple it is. If you're going to use it, run it on a local cluster like 'kind'. Some descriptions to try: * install a redis namespace with a redis cluster and a service in it * create an argocd application in the argocd namespace to install velero. * write a python script that lists all ec2 instances in us-east-1, and run it as a k8s job with the aws credentials already saved in the default namespace.. a somewhat longer description that also worked: given the following spec: --- kind: MagicHappens apiVersion: gptmagic.io/v1 metadata: name: foo spec: description: this is a freeform description field that will be sent to chatgpt to generate kubernetes resources dryRun: false --- Can you create more magic happens resources, each of which describes an argocd application that needs to be created to install a helm chart for one of the standard cluster addons that need to be installed on a cluster for it to be production ready. The description should be be freeform text like the following: "Create an argocd application in the argocd namespace to install istio from the helm chart with all the defaults" or "Create an argocd application in the argocd namespace to install prometheus and grafana, with an ingress enabled for grafana". Be very thorough and included as many apps that might be needed for a prod ready cluster using industry standard CNCF projects if possible. (this produces a list of additional resources for the operator, which the operator then goes on to create argocd applications for -- it also left comments with instructions on one of the resources for how configure it to work with your cloud provider something to note is that since you can run arbitrary containers with arbitrary commands, and chatgpt can write arbitrary code, you don't have to limit yourself to k8s stuff.. if you've got saas credentials on the cluster, you can just tell it to run a python script as a job to do whatever you want. Since most people are cowards, there's a dryRun field that defaults to true, so it only attaches the spec to the object. It is scary how well this works. https://ift.tt/4ScLqs6 April 18, 2023 at 12:09AM
Show HN: Trivai.app – AI powered trivia questions, with references Hi HN! As many of you, I've had a lot of fun playing around with LLMs the past few months and I wanted to show you what I've built. I made a trivia website using GPT3 a while back just to have something to play with. My initial interest was to see if I could get structured responses to build a UI around, and if I could get the LLM to refer back to what piece of text it used to create questions and answers with. The initial results were pretty good, but not good enough. Fast forward a few months, GPT 3.5 was released to the public and I was released from my work. I decided to pick this up again and have been making some changes. - I've generated almost 3000 questions. - I initially only let signed up users generate questions due to cost concerns. Since 3.5 is much cheaper, I've opened up the question generation for everybody. - I built a prompt comparison tool so I could tweak the prompt to get better responses. - I've added some more data to the questions. This includes a more free form explanation to the correct answer (separate from the references), and categories for all questions. - I've been working on a question improvement process. This means I collect issues, generate new variations of the question and let people vote on them. Voting and question improvement is currently only available to signed in users. I have many more ideas I'd like to explore, but I would appreciate your feedback and would be happy to answer any questions about the site or its development. You can access the references by pressing the explanation text when you've answered a question correctly. https://trivai.app April 17, 2023 at 11:13PM
Show HN: Ruby WhatsApp SDK Gem Whatsapp Ruby SDK gem Whatsapp released the Cloud API. I had an App that uses Whatsapp, and I extracted all the Ruby code that talks to the API into a gem and made it public. The gem provides the ability to connect with Whatsapp API. Amongst them, you can: - Interact with Business Profiles. - Interact with Phone numbers. - Interact with Media: audio, videos, images, stickers, templates, and documents (Upload/Download, send, receive). - Send and receive messages (text, templates and others). I'm looking for suggestions to make it better. I'm sure the people in HN could provide great feedback I could use to improve the library. https://ift.tt/fCuPtKk Thank you! https://ift.tt/fCuPtKk April 17, 2023 at 06:06AM
Show HN: Insight, an autonomous AI that can do medical research I am working on an AI that uses multiple LLM based agents to do medical research on any topic you choose! The program terminates after a set number of iterations and all of the findings are saved. Still a work in progress but it is showing some promising results imho! Would love to receive any critical and constructive feedback, collaborate, Review your PRs, or discuss your ideas!! https://ift.tt/MFpraDP April 17, 2023 at 03:15AM
Show HN: Let your body be the gamepad Hi HN, I made a keyboard emulator that tracks your body pose and emits the key presses accordingly. My main motivation was to make my kids move more on rainy days. I already made a couple of mini-games using the body pose [1-3], and those were definitely fun to make and play! However, once the kids learned the tricks, they got bored. I could only produce that much content myself, and soon realized that I lack time for churning out games. Finally, I decided to tap into an endless pool of PC games, preferrably simple and less addictive ones like the Gameboy and DOS games. This project has been also inspired by [4], which has been featured on HN recently. [1]: https://ift.tt/q2PJZQt [2]: https://ift.tt/4LB08E2 [3]: https://ift.tt/8I1fy2W [4]: https://ift.tt/fJWqBjY https://ift.tt/IE8tSTR April 17, 2023 at 01:12AM
Show HN: German Translation of the Rust Book I have just published a paperback and an e-book of the German translation of the Rust book from Steve Klabnik and Carol Nichols: Die Programmiersprache Rust https://rust-lernen.de/ The translation itself is available for free on GitHub. https://rust-lernen.de/ April 16, 2023 at 02:58PM
Show HN: Use GitHub Actions to generate a warm up routine Morning everyone - I made this because I really didn't want a new SaaS subscription to "be more productive". Turns out, you can do a lot with just a cronjob, GitHub Actions and CSV file! It works quite nicely because Issues created actually can have toggle-able checkboxes so you can mark yourself as you do them. https://ift.tt/OsBLfy2 April 16, 2023 at 01:55PM
Show HN: Pitchleague.ai – Perfect Your Pitch Deck Hey HN, We're excited to share that we've already assisted over 800 founders in refining their pitch decks with our recently launched Pitch League AI. Created during a one-day hackathon, our tool harnesses the power of GPT-4 to help founders iterate and enhance their pitch decks. We've observed founders uploading their decks multiple times and making improvements based on the AI-generated feedback. Our mission is to support as many founders as possible in raising funds for their startups, starting with perfecting their pitch decks. While Pitch League AI is still a work in progress, users have found it genuinely helpful thus far. The platform extracts text from PDFs and employs GPT-4 prompts to evaluate and ensure the completeness of pitch decks across various categories, including deck length, grammar & spelling, and the inclusion of vital information (e.g., problem, solution, team, etc.). We'd love to hear your thoughts and suggestions on how we can enhance Pitch League AI and any additional features you believe would be valuable. Looking forward to your feedback! Cheers. https://ift.tt/CTFHs8E April 16, 2023 at 01:46AM
Show HN: TYON, a Simple JSON Alternative TYON (typed object notation) is my attempt to address the main frustrations I have with JSON. 1. Key repetition - you can specify the key names once at the start of a list or map, instead of on each object separately. 2. Escaping strings - everything in a string is literal except for " which is escaped as "". This makes writing regexes and multiline text easier without introducing a bunch of different string styles or excess escaping, which I am not a fan of. 3. While not nearly as important as the first two to me, I did reduce symbol clutter when possible. Files are implicitly maps, keys don't require quotes in most cases, and you don't need commas between items. 4. Decoupling syntax and data formats - TYON has recommended formats for interoperability, but none of these are part of the core spec, so tools are equally welcome to just treat everything as a string. The linked repo contains the spec and a cli app that provides formatting, validation, and conversion to JSON. https://ift.tt/CrSsuqT April 15, 2023 at 03:10AM
Show HN: Example POC to run the Dolly V2 12B model in 8bit mode I banged this out today because nobody seems to have figured this out yet (and I wanted to play with this model). I was inspired by the fact that Simon Willison was struggling to get this running[0], so I wanted to take a crack at it! This is by no means "clean", but it is a baseline for others to hack from. Feel free to send over PRs and I'll land them! (I'd love it somebody used this to glue this into this webui[1].) 0: https://ift.tt/GsOT0qv 1: https://ift.tt/TGX4Yx6 https://ift.tt/yuZWTkq April 15, 2023 at 04:16AM
Show HN: Don't Hold Your Breath – Breathing Analysis with Polar H10 HR Monitor A person's heart rate fluctuates based on factors such as activity, environment, and mental state. Additionally, heart rate variations occur on a much shorter timescale, with changes happening every few seconds. During inhalation, heart rate slightly increases, and it decreases again during exhalation, a phenomenon known as respiratory sinus arrhythmia. There are several reasons for this. Firstly, an increase in volume within the thoracic cavity (the space between the ribs) leads to a corresponding drop in pressure, which is counteracted by a rise in heart rate to regulate blood pressure. Secondly, breathing is deeply intertwined with the autonomic nervous system, which involves the opposing activation of the parasympathetic ("rest and digest") and sympathetic ("fight or flight") responses. By measuring heart rate variability and regulating our breath, we can gain insight into our stress response and learn to control it. The Polar H10 heart rate monitor provides basic heart rate measurements from a chest strap ECG, compatible with a number of fitness tracking apps that monitor heart rate zones wirelessly using bluetooth. The device also provides raw sensor data including an accurate measure of the timing between heartbeats (interbeat interval, with millisecond resolution) and 200 Hz accelerometer data. In this project this information is used to measure breathing rate and heart rate variability, and explore the relationship between the two. https://ift.tt/8jJnYRk April 15, 2023 at 12:36AM
Show HN: WikiBinge – discover how all things are vaguely connected (2016) Connect two articles on Wikipedia, but do it the long way. I've always been a fan of the theory of six degree of separation, but it's an overused concept when exploring the Wiki-graph. Instead of showing the shortest path, which in my opinion is "boring" and ends up connecting super-important central articles, I came up with my own method: WikiBinge selects the smaller, less represented articles on Wikipedia. In a WikiBinge path, the underdogs are the kings! How does it work? It's pretty straightforward! Compute PageRank on the Wiki-graph and assign as weight of each edge the PageRank value of the destination node. A WikiBinge path is then simply a shortest path using these weights: the algorithm will then favor paths passing through articles with lower PageRank values. More on the motives to build this here: https://ift.tt/FHoOusm This is an older project of mine, but it never got much exposure, so I'm humbly submitting it now. https://ift.tt/t6h280J April 14, 2023 at 11:18PM
Show HN: Ampersand – “Terraform for Integrations” Hey HN! I’m one of the co-founders of Ampersand and we’re excited to launch our developer docs today! Ampersand is built for SaaS engineers who want to: - Read data from their customers’ SaaS (e.g. Salesforce, Hubspot). - Write data to their customers’ SaaS. - Subscribe to events happening in their customers’ SaaS (including creates, deletes and field updates). We feature a Terraform-like declarative interface for defining integrations, embeddable UI components for your users to set up and manage their integrations, and a management console for your team to monitor and troubleshoot. We’re launching our docs ahead of our product because we believe that docs are one of the most important things to get right in building a developer product, and we want to get early feedback on it. Looking forward to hearing your feedback in the comments below! https://ift.tt/02Wrhve April 14, 2023 at 02:38AM
Show HN: Google Analytics alternative with the most generous free tier Hi HN, As an indie hacker, the new Google Analytics (GA4) coming motivated me to look for a straightforward alternative that would also be affordable. I had a few basic product requirements and didn’t want to spend too much to replace a free product. There are a lot of great Google Analytics alternatives out there, but the pricing didn’t seem right. As someone who likes to just build things, many of which aren’t businesses yet, it didn’t make sense to pay for options like Plausible and Fathom out of the gate. So I joined with a friend to build Beam Analytics. Beam gives you all the standard web analytics. It also comes with easy to create funnels so you can see how users move through your site. And we have a great proxy for cohort retention that doesn’t need you to log any data with us. It’s cookie-less and GDPR compliant. The free tier is 100k page views per month so hopefully you’ll give it a try. There’s also a Wordpress integration to make integrating with WordPress sites as easy as a single click - https://ift.tt/EAp1JGX . Appreciate your feedback. You can also email us at hi (at) beamanalytics.io or DM me on twitter @TheBuilderJR. https://ift.tt/JTGrRyw April 12, 2023 at 07:10PM
Show HN: NeverPrinter – find and use thousands of nearby printers Hi all, My friends and I have created a Chrome extension and we are looking for feedback on whether people find it useful or not. The extension is intended to serve as a home printer substitute for people (like us) who don't want or need their own printer at home. It makes it easy to send documents to nearby office supply / shipping stores for printing and pickup. Installing the extension adds a printer named NeverPrinter to your list of available printers in Chrome. When you print a document with NeverPrinter, a new tab opens allowing you to select which nearby store you want to send the document to. This is the latest iteration in an ongoing project my friends and I have been working on. We would love to hear any positive or negative feedback. You can get the extension by going to the Chrome Web Store and searching for "NeverPrinter." Or you can visit https://ift.tt/pcePA1J , which will redirect you there. https://ift.tt/BGnZwHY April 13, 2023 at 11:18PM
Show HN: GPTCache – Redis for LLMs Hey folks, As much as we love GPT-4, it's expensive and can be slow at times. That's why we built GPTCache - a semantic cache for autoregressive LMs - atop the vector database Milvus and SQLite. GPTCache provides several benefits: 1) reduced expenses due to minimizing the number of requests and tokens sent to the LLM service 2) enhanced performance by fetching cached query results directly 3) improved scalability and availability by avoiding rate limits, and 4) a flexible development environment that allows developers to verify their application's features without connecting to LLM APIs or network. Come check it out! https://ift.tt/z2Rj8yF https://ift.tt/tU1wYb5 April 13, 2023 at 03:14AM
Show HN: I’m building an autonomous business run by ChatGPT Hey HN!! I just shipped a project called Airfeed: https://airfeed.co/ Here's how it works: 1. You tell it the research topics you're interested in following This can be anything -- LLMs, chatbots, image generation, scaling model inference, small language models, datasets, etc. 2. Every morning, it filters new AI research papers for quality work that is relevant to your configured topics, and sends you an email summary. Here's a sample email: https://ift.tt/EkcW6LB --- As a fun experiment, I've made everything completely autonomous: Every morning, ChatGPT takes care of filtering/processing all research papers & writing each email. --- Why I built this: I think there needs to be a better way for engineers, researchers, and AI product builders to stay up to date on the latest AI research that's relevant to whatever they're working on. For someone building LLMs, this could mean keeping up with research papers covering multiple topics, ex: scaling attention, model architecture, new datasets, new fine-tuning techniques, etc. --- How this is different from other newsletters: This isn't a generic AI newsletter. It's research-focused & personalized, since it only highlights the papers that might be relevant to you (based on your specific topics). I found this to be useful, since a lot of papers are irrelevant and/or low quality. --- When building maroofy.com [1], I would regularly read the latest research papers on everything related to: contrastive learning, vector embeddings, music classification, etc. So, I thought it would be nice to build something that filters/summarizes just the new research papers covering topics I care about, and sends me the top ones in a daily, morning email. Would love any feedback!! :D [1] https://ift.tt/O37Ip5x https://airfeed.co/ April 13, 2023 at 03:22AM
Show HN: GPT-4-powered web searches for developers Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a step-by-step guide complete with citations ( https://ift.tt/wV9sCkE... ) while Phind in default mode meanders a bit and answers the question very generally ( https://ift.tt/RAJ2ELh... ). GPT-4 is significantly more concise and “systematic” in its answers than our default model. It generates step-by-step instructions over 90% of the time, while our default model does not. We’re particularly focused on ML developers, as Phind can answer questions about many recent ML libraries, papers, and technologies that ChatGPT simply cannot. Even with ChatGPT’s alpha browsing mode, Phind answers technical questions faster and in more detail. For example, Phind running on “Expert” GPT-4 mode can concisely and correctly tell you how to run an Alpaca model using llama.cpp: ( https://ift.tt/FLVaiy1... ). In contrast, ChatGPT-4 hallucinates and writes a make function for a fictional llama.cpp. We still have a long way to go and would love to hear your feedback. https://www.phind.com April 12, 2023 at 11:14PM
Show HN: Llama.go – port of llama.cpp to pure Go It's April 12 - The First Man in Space* Day - and I'm releasing #ML framework I've been building for the last month :) It's written in #Go and allows #LLaMA #GPT inference having just regular PC - so no monster GPU cluster is needed to start experiment with: https://ift.tt/2NcBJXh The V1 is using FP32 math only, but will work with AVX2 data types and INT8 quantisation soon. * The first man in space was Yuri Gagarin from USSR https://ift.tt/2NcBJXh April 12, 2023 at 11:12PM
Show HN: WallStreetGPT:ChatGPT plugin for connecting to brokerage and trading ChatGPT Plugins are in developer alpha, but thought to share one. WallStreetGPT allows you to: 1) Fetch real time quotes (crypto or stocks) 2) Get analytics 3) Do portfolio optimization (Markowitz, etc) 4) Submit live orders (yes.. but need a brokerage account that has API connectivity like IB or Alpaca) https://twitter.com/nextworddev/status/1645814196670529538 April 12, 2023 at 12:19AM
Show HN: GPT–LLM native macOS app with time travel, versioning, search Hey everyone! I made a Mac app for exploring large language models. It’s fast, small, has a tiny memory footprint. It’s immutable by design with both immediate time travel and automatic versioning as foundational elements. The app is written in Swift and a bit of Rust for the tokenizer. I used SwiftUI for structure and animations and Cocoa for advanced behavior. All storage is SQLite and local-only. You can go through the database as needed and backup it as well. The app has support for variants, which is the `n` parameter in the OpenAI chat completion API—equivalent to the drafts feature in Bard. It shows model- and ChatML-aware tokens and cost, and it dynamically adjusts response length in function of prompt length and context length. It supports hiding runs that are not useful, marking the ones that are notable, and going through the ancestry of the current run. It also has support for examples, as specified in ChatML, conversation names and personal and local-only notes. The full-text search works across all stored text and it has support for `all`, `any`, `prefix` and `phrase` matching; the results are time-ordered rather than ranked for the time being. There are several shortcuts and more are coming so that the app can be used entirely by keyboard. You can export to JSON and all data is exported. The app is sandboxed and notarized. The API keys are stored securely in the Keychain. Next I plan to implement combinatorial runs (mixing multiple values of the same parameter and multiple models as well) and full Markdown support. Currently only OpenAI’s conversational models are supported (GPT 3.5, GPT 4 8K, GPT 4 32K), but I’ll be adding support for local models and custom ChatML endpoints as soon as possible. Give it a try. Any and all feedback welcome! Thoughts and questions as well! William https://thellm.app April 11, 2023 at 11:34PM
Show HN: Wolverine: Give your Python scripts regenerative healing abilities Run your scripts with Wolverine and when they crash, GPT-4 edits them and explains what went wrong. Even if you have many bugs it will repeatedly rerun until it's fixed. Demo video on twitter: https://twitter.com/bio_bootloader/status/163688020830443110... https://ift.tt/jUicuQP April 11, 2023 at 04:01AM
Show HN: Rust Guideposts – 100+ topics to help learn about Rust I'm teaching Rust to compsci students and recent grads who are joining tech teams. I'm creating a guide of many Rust topics and their summaries. https://ift.tt/xDN8doB The guide is free and open source. I'm seeking ideas for improvements, to help newcomers to Rust and its ecosystem. In addition to the repo, the guide is available as an ebook PDF, with pay-what-you-wish pricing. https://ift.tt/tSohDsr My goal is to help many people learn about Rust, so I greatly appreciate your advice and you sharing the guide if you wish. Thanks! April 11, 2023 at 12:47PM
Show HN: Skip the SSO Tax, access your user data with OSS As the former CTO of an Insurtech and Fintech startup I always had the “pleasure” to keep regulators and auditors happy. Think of documenting who has access to what, quarterly access reviews, yearly audits and so on… Like many others we couldn’t justify the Enterprise-plan for every SaaS tool to simply get access to SSO and SCIM/SAML APIs. For Notion alone the cost would have nearly doubled to $14 per user per month. That’s insane! Mostly unknown to people, SSO Tax also limits access to APIs that are used for managing user access (SCIM/SAML). This has proven to be an incredibly annoying roadblock that prevented me from doing anything useful with our user data: - You want to download the current list of users and their permissions? Forget about it! - You want to centrally assign user roles and permissions? Good luck with that! - You want to delete user accounts immediately? Yeah right, like that's ever gonna happen! It literally cost me hours to update our access matrix at the end of every quarter for our access reviews and manually assigning user accounts and permissions. I figured, there must be a better way than praying to the SaaS gods to miraculously make the SSO Tax disappear (and open up SCIM/SAML along the way). That’s why I sat down a few weeks ago and started building OpenOwl ( https://ift.tt/j4zrqxU ). It allows me to just plug in my user credentials and automatically download user lists, including permissions from SaaS tools. Granted, OpenOwl is still a work in progress, and it's not perfect. At the moment it's limited to non-SSO login flows and covers only 7 SaaS vendors. My favorite part is that you can configure integrations as “recipes”. The goal was for anybody to be able to add new integrations (IT managers and developers alike). Therefore you ideally don’t even have to write any new code, just tell OpenOwl how the new SaaS vendor works. What do you think? Have you dealt with manually maintaining a list of users and their permissions? Could this approach get us closer to overcoming parts of the SSO Tax? https://ift.tt/j4zrqxU April 11, 2023 at 06:10PM
Show HN: The Coolest advancements in AI this week I hope you find these AI breakthroughs and projects as exciting as I do! I'd love to hear your thoughts, opinions, and predictions about these advancements in the comments below. Let's have a lively discussion! I'm also excited to announce that I've started a free daily newsletter called "The AI Revolution" to help you stay updated on the latest AI advancements, all in one place. Today's post is just the first issue, and I'm completely open to suggestions for improving tomorrow's newsletter. Your feedback will be invaluable in shaping this resource. Subscribe to "The AI Revolution" and never miss an update: https://ift.tt/lA1y6FX And feel free to follow us on Twitter for more recent updates: https://twitter.com/TheAIRevolu Looking forward to your thoughts and ideas! https://ift.tt/j6Qwmdx April 10, 2023 at 06:05PM
Show HN: Hacker News from Alternate Dimension (With Everything LLM-Generated) I recently discovered that LLMs can generate hilarious tech article titles, so I took it to the next level by generating coherent and entertaining comment threads, article content, and images. It will be automatically updated, so you'll never get bored. Enjoy! P.S. I've added robots.txt so I hope it doesn't get indexed. https://ift.tt/IW0tF1h April 9, 2023 at 12:36AM
Show HN: Compress GPT-4 Prompts Hey HN! I recently built Prompt Reducer, an app that makes it easier to compress GPT-4 prompts. The main goal is to reduce the number of tokens in each prompt, thereby reducing the cost of running GPT-4. I figured since @gfodor tweeted about compressing GPT-4. It’s still early, and it does not work perfectly, but I’d love to hear any feedback or suggestions for how to make it faster or more efficient. https://ift.tt/M6AmViv April 8, 2023 at 04:39AM
Show HN: Askbend – SQL-Based Knowledge Base Search and Completion AskBend is a Rust project that utilizes the power of Databend and OpenAI to create a SQL-based knowledge base from Markdown files. You can easily use blogs or documents as data sources and host your own instances. April 8, 2023 at 12:22AM
Show HN: ChatGDB – GPT-Powered GDB Assistant ChatGDB is a tool designed to superpower your debugging experience with GDB, a debugger for compiled languages. Use it to accelerate your debugging workflow by leveraging the power of ChatGPT to assist you while using GDB! It allows you to explain in natural language what you want to do, and then automatically execute the relevant command. Optionally, you can ask ChatGPT to explain the command it just ran or even pass in any question for it to answer. Focus on what's important - figuring out that nasty bug instead of chasing down GDB commands at the tip of your tongue. See it here: https://ift.tt/OuvNdji https://ift.tt/OuvNdji April 7, 2023 at 10:26PM
Show HN: Find Perfect App for Self Hosting The website is just another interface to awesome-selfhosted[0] list. I am no front-end developer so please bear with me as I improve the design and add more capabilities like filter and sort. The website looks good on desktop and on mobile in landscape mode. [0]: https://ift.tt/WO7PeC5 https://ift.tt/bha7cXD April 7, 2023 at 11:23PM
Show HN: Scan your blog for broken outgoing links I built this small proof-of-concept interface that lets you scan a URL or the pages in a .XML sitemap for broken outgoing links. I use this to find issues with links in my own blog and I'm wondering if this is useful for others! I also have some cases of false positives showing up and I'd be interested in knowing if you have suggestions to better handle those cases. https://ift.tt/lnqvQui April 7, 2023 at 01:38PM
Show HN: I built a Hackable Hacker News (reprogrammable in-browser) Explanation/How to use: https://www.youtube.com/watch?v=-LsnmoSEEjI It works as a general-purpose news reader too! Feel free to give me your thoughts and suggestions. Hope it's something you all find fun! https://ift.tt/6v0MuGe April 7, 2023 at 05:20PM
Show HN: Machato — A native macOS client for ChatGPT Machato is a tiny ChatGPT client that supports all basic features, and more ! I was frustrated with other native implementations that focused on quick access but didn't give easy access to a history of what has been said. Since ChatGPT is a learning tool for me, I'm always ruffling through past conversations. The client supports markdown rendering as well as LaTeX. Feel free to try it out ! For those who see this thread early, you can use the promo code EARLY_BIRD to get a free lifetime license. Let me know if some aspects can be improved or if there are features you'd like to see implemented in native clients. EDIT: Since the early bird discount has expired before this post could reach HN, I'll leave you with 50% off with the code MACHATO50 ! https://ift.tt/a1tTK7N April 6, 2023 at 10:22PM
Show HN: I feed all my daily entries to an AI (ChatGPT) Hello there! I hope you're doing well today! I wanted to share something with you. Recently I was on the hunt for the best way to journal daily. Well, I had this idea - what if I could feed all my daily entries to an AI (ChatGPT), and create a friendly, supportive character like Socrates or Simon Sinek? This way, I could ask any questions about my life and mental health, and get some amazing advice on how to improve myself! The results have been absolutely mind-blowing ! I even made a short GIF to show you how it works - check it out! - https://ift.tt/jNp1AU6 I've shared this with my friends, and they loved it so much that they've been asking me to create a full-featured journalling app with an AI assistant! What do you think? Would you be interested in using an app like this? I'd love to hear your feedback and thoughts on this. Please feel free to drop a comment and let me know what you think! Right now, I'm just collecting a waitlist of people who are interested in the app, so if you're interested, here is a link for signup to waitlist - https://ift.tt/fcDSpKE .If I can get 100 people on the waitlist in the next few days, I'll launch the app! April 6, 2023 at 12:16PM
Show HN: AI-Less Hacker News Lately I've felt exhausted due to the deluge of AI/GPT posts on hacker news, and have seen similar grumblings. I threw together this frontend that filters out anything with the phrases AI, LLM, GPT, or LLaMa for use until the hype dies down a bit. Before anyone asks, yes I did try to use ChatGPT to help, and while the code it provided was helpful, it needed some heavy bug-fixing. https://ift.tt/Udi0R1L April 6, 2023 at 12:24AM
Show HN: GPT-4 powered brand name generator As a fun weekend project to take a break from the everyday work-university cycle, I've messed around with OpenAI's GPT-4 API and created a simple name generator with it. In the coming days, I'll be adding more features. https://www.namique.xyz/ April 5, 2023 at 04:49AM
Show HN: Live coaching app for remote SWE interviews, uses Whisper and GPT-4 Posting from a throwaway account to maintain privacy. This project is a salvo against leetcode-style interviews that require candidates to study useless topics and confidently write code in front of a live audience, in order to get a job where none of that stuff matters. Cheetah is an AI-powered macOS app designed to assist users during remote software engineering interviews by providing real-time, discreet coaching and integration with CoderPad. It uses Whisper for audio transcription and GPT-4 to generate hints/answers. The UI is intentionally minimal to allow for discreet use during a video call. It was fun dipping into the world of LLMs, prompt chaining, etc. I didn't find a Swift wrapper for whisper.cpp, so in the repo there's also a barebones Swift framework that wraps whisper.cpp and is designed for real-time transcription on M1/M2. I'll be around if anyone has questions or comments! https://ift.tt/X4arBM2 April 5, 2023 at 05:06AM
Show HN: CartoSVG – create beautiful map visualizations easily This project aims at making the creation of rich interactive maps easy, with no compromise on the visual quality. A goal is also to export the final SVG as lightweight as possible, with no dependency on external libraries, which are usually needed to have interactive maps on a website. Feel free to explore the examples (the “examples” dropdown at the top-right) to explore what is possible to design with CartoSVG. https://cartosvg.com April 5, 2023 at 12:35AM
Show HN: Deno SaaSKit Hey all, Our community wanted to learn how to do more with Fresh, adding auth, databases, logins, billing, etc., so while we were creating educational resources, we also decided to build and open source a SaaS template written in Fresh/Supabase. Note this is in beta and our SaaS features are limited, but we have a roadmap to 1.0 and welcome any contributions/feedback/etc. We'd love to get your thoughts on this project! https://ift.tt/mFDn54g April 5, 2023 at 12:53AM
Show HN: Enhancing GPT with domain knowledge using vector databases Hey HN, Autoregressive language models such as GPT and LLaMA have a tendency to hallucinate when asked about out-of-domain questions. An easy way to minimize these hallucinations is to supply LLMs with external sources of domain-specific data using a vector database. To this end, we built OSSChat, a GPT- and Zilliz-powered project that you can use to ask questions about, summarize, and analyze open source projects by indexing the documentation and automatically searching for relevant documents when asking a question (these documents are then injected into the LLM as prompt). While we decided to focus on open source projects - Pytorch, Transformers, and Milvus - for now, OSSChat is easily extensible to a variety of other types of data. We are committed to adding support for more projects in the future, so don't hesitate to let us know your favorite project! site: https://osschat.io discord: https://ift.tt/hJxYgME blog: https://ift.tt/s7hwiqd Enjoy the project! https://osschat.io April 4, 2023 at 10:54PM
Show HN: Daba – Turn your JSON into a database Hi all, I built this tool when I needed a simple LocalStorage-esque database for a client project, and figured others might want something similar. Basically turns your JSON into a query-able, hosted database in seconds. You can read/update/delete JSON files by path, just like you would in Javascript. So, something like get(”users[7].address”) And while we’re at it, I also built a simple file storage service where you upload a file and it gives you the URL back. A lot of my (and other devs friends') side projects will never require more data than a JSON file can handle. Yet we always have to go through the hoops of setting up and using databases meant to handle huge amounts of data. There are many other services that could benefit from the same minimalist philosophy. The idea is to have a bunch of building blocks of different services, and let the developer scale up/down the complexity as they see fit. I'm working on more services for daba (In no particular order: SQLite db?, auth, emails, …) You can use this for any applications where the data can fit in a JSON file. (e.g. Website CMS, blog, portfolio, small mobile apps, internal tools, …). You’ll be surprised at how much data a 20mb JSON file can hold: https://ift.tt/tK7Xyb2... Let me know what you think https://www.daba.so April 4, 2023 at 02:24AM
Show HN: Cloud.museum the first SSG coded by ChatGPT ChatGPT can code pretty well but not without some help. After 100+ interactions here is the first ever static site generator coded entirely by ChatGPT. There is a NodeJS and even a Swift version. What do you think ? https://cloud.museum April 3, 2023 at 05:44AM
Show HN: Shhhbb, an SSH BBS Hello all :) I made this BBS for fun and thought you all would enjoy it. It's not perfect, but it's been a fun exercise! see it: https://ift.tt/2cXhN76 try it: ssh -p 2223 shhhbb.com host it: https://ift.tt/zG3m8TS why? Every year I challenge myself in some new way, this year it is to push one project per week. You might recognize my static site generator [0] or my releaser for go [1] from previous posts as one of these weekly projects. If you want to join me in doing this, it's been a blast and I highly recommend it! Maybe we can chat on the bbs about it :) [0] - bearclaw tiny static generator - https://ift.tt/7mqTAwR [1] - release.sh release builder for go - https://ift.tt/7mqTAwR need: I'd love a few co-conspirators, or even some new friends for the bbs software or the bbs itself. A lofty nice-to-have goal is meeting a few other similarly motivated people to conspire with on a weekly basis. If that's you, drop me a line! goals: I have about half of an admin interface endpoint pushed up, which I'd like to finish. I realized mid-commit that I'd lacked some other material in a previous commit, and in pushing it up, I ended up pushing half the admin feature. Stay tuned for that. I'd also like to implement a feature where I surrender the socket to a new process so I can upgrade the binary without dropping all of the connected users. I'm not sure on the feasibility of this, but all the words fit together, so it'll be tried. https://donuts-are-good.github.io/shhhbb/` April 2, 2023 at 10:10PM
Show HN: iOS App to build your own content feed Hey Folks, looking for some feedback on an iOS app I built. I'm not that great at UI and would love any feedback when it comes to just overall UX. You can download the TF here: https://ift.tt/NTKV6xs I've been really annoyed lately in getting a good content feed. Its a mix of a traditional RSS app but you could also important things from Twitter and other websites. April 2, 2023 at 05:37AM
Show HN: Build your own no-code editor with Reka.js Much of the complexity surrounding building no-code editors come from architecting the state management system to power such editors: how can we allow end-users to create and edit entire UI components directly from the browser? Reka solves this by providing an AST-powered state system that enables end-users to create UI components that are nearly as complex as ones that developers could write in code; along with an interpreter to efficiently compute an output that could be rendered on the browser. Furthermore, Reka provides additional extensions, such as enabling real-time collaboration via CRDTs; or you could build a custom extension to support additional functionalities such as a commenting system. All that's left is for you to build your own UI abstractions on top of Reka — designing your editor UI/UX and providing easy-to-use buttons/controls for your end-users to mutate the underlying state in Reka. Github: https://ift.tt/c9diN5S https://reka.js.org April 1, 2023 at 05:00PM
Show HN: AI Shakespeare These days thinking of ways to uniquely show off a text to speech model is tough, as there are a lot of them out there. We thought it would be fun for April 1 to show something a bit on the silly end of things -- we trained our TTS model on "Shakespearean" theatrical voices, and used GPT to generate short plays which are then "acted" out. This lets us show the versatility of our model, that we use in more "serious" settings for generating branded voices for particular languages or accents. It should be noted, the dataset is of our own curation; all voice actors were compensated with full knowledge of being used for TTS and were thrilled to be part of a creative project like this. We resample the speaker embedding space to find voices that are different from any one particular actor. https://ift.tt/ZJw15mV April 1, 2023 at 02:00PM
Show HN: Coursemate, connect with other self learners Hey Hacker News! My name is Collin, 18 years old and doing a gap year after finishing high school last year. This was my first real project after starting to learn web development around 5 months ago. I came up with this idea as it was a real pain for me to find other people from my country and especially my age, learning and taking online courses about the same stuff online. Lots of these online courses include their own discord communities and forums, but I still found it very hard to connect with other people in there. Thats why I built Coursemate. I would love to get your feedback on it! :) https://ift.tt/yVOopxE April 1, 2023 at 02:08PM
Show HN: ParallelGPT – Batch processing with ChatGPT on low-code spreadsheet UI We made ParallelGPT - a tool that lets you bulk process chatGPT on a spreadsheet UI instead of one-by-one conversation style. Hopefully this saves you time and hassle - especially if you want to build an operational process around it and want to collaborate your team. You can give it a quick spin on this live demo playground: https://ift.tt/dYw6zvO... I am the co-founder of Rowy( https://www.rowy.io ), an open-source low-code platform, and we built ParallelGPT as a fun showcase of what you can do with low-code. There are tons of exciting AI apps you can build with low-code, and we're always happy to chat about any ideas you have and assist on our Discord. https://ift.tt/erpL7HQ April 1, 2023 at 06:17AM
Show HN: DigicamFinder – open-sourced DPReview camera data Ever since the DPReview closure announcement https://ift.tt/wjItsGc we were thinking how to preserve the 25 years of valuable DPReview camera data. Archive.org has been great, but it's not usable by the general public. The best way to keep it safe going forward, is to have the community own it, so we open sourced it: https://ift.tt/XFZ41E5 I'm aware of a number of attempts to make product data open-sourced, but none have the power of the photo geeks behind it :) Thoughts or ideas? + really looking for some contribution love. https://ift.tt/IDYSGk8 April 1, 2023 at 04:12AM
Show HN: Simply explain 20k concepts using GPT Hi HN! I made a tool that autogenerates simple, high-level explanations of concepts and organizes them in a somewhat university course-like structure so that it's easier to see how things are structured. Currently it has about 20,000 concepts on a range of topics but that's just what I generated so far, it should work with more obscure topics in the future. I love learning about random topics where I don't have a good background in like history or linguistics, but it's hard to figure out what topics there (you don't know what you don't know) are in certain fields and what they are even about, so this was a way to get the high level idea about random things that I wanted to know about. It also only uses the information in the GPT model at the moment, so obviously information can't be trusted completely and you should definitely double check any information you read here by Googling. I'm thinking of doing the Bing Chat approach for the next version and adding references, but don't have that yet Hopefully someone else finds this useful even if it's not perfect! https://ift.tt/iPbHpnT April 1, 2023 at 03:54AM
Show HN: Cadseer. a parametric solid modeling CAD desktop application Cadseer is in the same genre as: solidworks, inventor, freecad etc... Cadseer is alpha software, so lots of missing features, bugs, crashes, file incompatibilities etc... About me: I spent 15 years designing stamping dies on a high end cad system. During that time, I also developed and marketed extensions/plugins toward that cad system. Through that experience, I came disillusioned with 'vendor lock-in' and proprietary software in general. I basically retired, took the vow of poverty and moved all my computing to open source. I have since, and continue to, try and improve the open source cad environment. https://ift.tt/UAjmMZC April 1, 2023 at 12:05AM
संदेश
