Show HN: Yakread – An RSS reader powered by machine learning https://bit.ly/435tL6L

Show HN: Yakread – An RSS reader powered by machine learning This is a web-based reading app I've been working on since August. The main differentiator is that Yakread uses machine learning to rank the articles in your feed: as you click on articles from a particular RSS/newsletter subscription, other articles from that subscription will tend to be ranked higher in the future (via a bandit algorithm). Yakread also uses ML to recommend articles that other users have read, so your feed will have articles in it even before you sign up and add your own subscriptions. For the recommendations, I'm using the collaborative filtering implementation from Spark MLlib[1]. I model RSS feeds instead of individual articles: when you click an article, that counts as a "point" for that article's RSS feed; at recommendation time, the algorithm first selects an RSS feed to recommend, and then it picks one of the popular/recent articles from that feed. To counter popularity bias, I have a pre-ranking step that probabilistically filters out RSS feeds that have already been recommended a lot. I manually approve all RSS feeds before they're eligible to be recommended. In addition to scrolling through the algorithmic feed, you can read articles chronologically on the subscriptions page, which I sometimes prefer when I have a larger chunk of reading time. There's also a daily digest email that lists new articles from your subscriptions; skimming that is part of my morning routine. I find the whole system gives me a nice balance between algorithmic filtering and manual control. This is the culmination of the past four years I've spent as a full-time bootstrapped founder; Yakread both scratches a personal itch and attempts to fix various deficiencies that my previous businesses have had. In a nutshell, I've come to believe that "discovery is a feature, not a product," which is why Yakread is a full reading app instead of a standalone recommender system like my previous products.[2] From a business perspective, the recommendation algorithm is primarily intended to help onboard new users quickly/easily. More ideologically, I think RSS is ready for a comeback :). [1] https://bit.ly/3MTxcYJ... -- I'm using the implicit feedback setting. [2] Show HN for Yakread's immediate predecessor, The Sample: https://bit.ly/3h1CcKK . The Sample does bring in $1k or so per month, but long-term retention is too low for me to grow it sustainably. https://bit.ly/3MRSdmu May 24, 2023 at 06:29PM

Show HN: I made a Chrome extension to hide history in ChatGPT https://bit.ly/43pmHC0

Show HN: I made a Chrome extension to hide history in ChatGPT https://bit.ly/3q05IYi May 24, 2023 at 12:15PM

Show HN: Mental Models for Startup Founders https://bit.ly/41ZxRMp

Show HN: Mental Models for Startup Founders Hello HN, I launched Wingify/VWO (Visual Website Optimizer) here on HN in 2010. The initial momentum and feedback I got from this place was a key reason I was able to profitably bootstrap the company to roughly ~$30MN ARR. Over the last 2 years, I have been writing a book for startup founders that's informed by my experience with Wingify and many failed attempts before it. It's finally done, so thought of launching it on the same forum where it all started for me :) There are a total of 68 mental models covering various aspects of building a startup: - Choosing markets - Building products - Ecosystems and partners - Thinking about Moats - Approaching marketing - B2B v/s B2C - Hiring & culture Unlike other books, I'm not sharing my story and neither take a very prescriptive approach. Rather, I use mental models to shine light and provide a tractable way of looking at problems an entrepreneur encounters during her startup. I understand that entrepreneurship cannot be systemized, but I'm hoping some of the mental models I share help in clearer thinking and faster decisions. Would love your feedback on the book: https://bit.ly/45wriUz... If you find it useful, please share it with others in your network. https://bit.ly/3BVbWLK May 24, 2023 at 07:27AM

Show HN: Defguard – open-source security army knife (Identity,MFA,VPN,Yubikey) https://bit.ly/3WyeUzB

Show HN: Defguard – open-source security army knife (Identity,MFA,VPN,Yubikey) https://bit.ly/3BQY9pt May 24, 2023 at 11:27AM

Show HN: Dark Mode for HN https://bit.ly/3MQCSCP

Show HN: Dark Mode for HN https://bit.ly/3MTWGoY May 24, 2023 at 09:41AM

Show HN: JavaScript Office Library: View and Convert Word, Excel, PowerPoint https://bit.ly/3OvEqn3

Show HN: JavaScript Office Library: View and Convert Word, Excel, PowerPoint Hi HN, Igor here. We’re super excited to officially launch PSPDFKit for Web Standalone’s Office-to-PDF functionality ( try the demo [0] ). PSPDFKit for Web Standalone is a JavaScript document library that runs entirely in the browser - no external dependencies or MS Office licenses required. It’s compatible with any JavaScript framework. What differentiates our Office-to-PDF from others is that it’s built from the ground up with no reliance on open source. When converting to the PDF format, it enables additional document capabilities, like page manipulation, redaction, or editing content. Office document capabilities [1]: - View and open Word, Excel, and PowerPoint files - Convert to PDF, PDF/A, or PNG - Print - Preview Office-to-PDF capabilities [1]: - Edit content - Annotate - Assemble multiple documents - Manipulate pages - Create and fill forms - Add signatures - Redact content Our documentation includes sample code [2] and quickstarts for JavaScript [3], React [4], Vue.js [5], Angular [6], SharePoint [7], and others. Let us know what you think or if you have any questions. [0] https://bit.ly/3ojdJr3 [1] https://bit.ly/3OAbg6m [2] https://bit.ly/43fTwB4 [3] https://bit.ly/3q9bvLu [4] https://bit.ly/3BS6NnI [5] https://bit.ly/3pX165c [6] https://bit.ly/43nlHho [7] https://bit.ly/43ijvYE May 23, 2023 at 10:10AM

Show HN: MrScraper AI – Dead simple web scraper (powered by AI) https://bit.ly/3ooqzUO

Show HN: MrScraper AI – Dead simple web scraper (powered by AI) I've decided to test a new approach in my web scraping app. What do you think? https://bit.ly/3BPx2v5 May 23, 2023 at 08:20AM

Show HN: I made Hazumi, a modern HN reader for iOS https://bit.ly/3BPqP2f

Show HN: I made Hazumi, a modern HN reader for iOS Hello HN, I'm thrilled to announce the launch of my first app, Hazumi, a Hacker News reader, available for free on iOS! I’ve been lurking on HN for around 2 years while working on this project seeing people post amazing HN reader apps of their own. I’ve always figured Hazumi wasn’t good enough yet to post here but if I wait around until I’m ready, I’ll probably never share so here goes… Hazumi is a modern Hacker News app for your pocket with some intentional limitations. Stories are displayed on a simple colourful card, with images, that condenses all the information you need at a glance. Out of the box you get accessibility features for system settings like light/dark mode and text size. Others are controlled in app for opening stories in a Web View vs externally via Safari, defaulting to Reader Mode and reducing animation bounciness. You can browse top, new and best sections, limited to 30 stories each, which refresh every hour on the server. I’m not a fan of infinite scrolling or spending a lot of time reading news. I just want to get in and get out while keeping up on the latest. Other notable features: - Basic search - Widgets for your Home and Lock Screen - Apple Watch app - Warns you of non-HTTPS links There are a few “PRO” features that require a subscription ($/€1.99 monthly): - AI summaries of comments on stories that have at least 30 root level comments - In app newsletter (yesterday’s top 10 stories) - Bookmarking with iCloud support - Themes (change the colour of the cards) - Supporting indie developers and keeping the lights on for Hazumi Working on: - Better comments/tappable links - Enhancing search - More themes Being the first version, it's very early days for Hazumi and there are bugs that I’m working on fixing. I'm eager to improve it and shape its future based on your input. I welcome any feedback you may have, whether it's about existing features or ideas for new ones. Your thoughts will be instrumental in shaping Hazumi, making it an even more useful tool for tech news enthusiasts. Please give it a try and let me know your thoughts. P.S. Shout out to MB and MC for your awesome feedback during the TestFlight beta! https://apple.co/3BQLfIg May 22, 2023 at 03:31PM

Show HN: Ntfy.sh – open-source push notifications via PUT/POST https://bit.ly/45nIT12

Show HN: Ntfy.sh – open-source push notifications via PUT/POST https://bit.ly/3FMWaTq May 22, 2023 at 10:01PM

Show HN: I solo developed an action-roguelite and launched it today https://bit.ly/41VwKgZ

Show HN: I solo developed an action-roguelite and launched it today It's my first steam game, I'm very pleased with how it came out. It's the largest person project I've ever made. I'm happy to answer any questions. https://bit.ly/422HLgu May 23, 2023 at 03:12AM

Show HN: DB-GPT, an LLM tool for database https://bit.ly/45nw1be

Show HN: DB-GPT, an LLM tool for database https://bit.ly/3BP6MRv May 23, 2023 at 02:40AM

Show HN: I ported my Tetris built with SDL2 to WebAssembly https://bit.ly/3BSgvXn

Show HN: I ported my Tetris built with SDL2 to WebAssembly https://bit.ly/3onENVY May 23, 2023 at 12:46AM

Show HN: Aimless.js – the missing js randomness library https://bit.ly/43k2hdn

Show HN: Aimless.js – the missing js randomness library https://bit.ly/43k2ixX May 22, 2023 at 11:41PM

Show HN: Blotter – An interactive, never ending music video https://bit.ly/3MsnfQG

Show HN: Blotter – An interactive, never ending music video One day I was listening to a playlist and wished there could be some cool visuals to go along with it. Blotter is a proof of concept I hacked together that does a bit of audio recognition combined with a few generative AI models (both text and img) to create visuals that are relevant to the song. The video stream is generated in real time at 24fps - you can try it yourself by requesting visuals in the Twitch chat using the "!v" command! Right now it's mostly a fun hack project, but I am tinkering with new model architectures for higher fidelity video as well as an interactive tool so people can make videos with their own audio files. I'd love to hear any feedback or suggestions, thanks! https://bit.ly/3MtgI8n May 22, 2023 at 11:21PM

Show HN: Airbroke, open souce error catcher https://bit.ly/3IwEA9Q

Show HN: Airbroke, open souce error catcher tired of errbit https://bit.ly/3OwVnxj May 22, 2023 at 01:56PM

Show HN: ClipBase - YouTube Full Text Search – Search videos by words spoken https://bit.ly/3MqcNsW

Show HN: ClipBase - YouTube Full Text Search – Search videos by words spoken https://bit.ly/3Ipzufu May 22, 2023 at 09:39AM

Show HN: Rust Port of Pwnpasswordsdownloader https://bit.ly/3C5tYLH

Show HN: Rust Port of Pwnpasswordsdownloader https://bit.ly/43jtwom May 22, 2023 at 10:18AM

Show HN: WikTok – A Recommendation UI for Wikipedia https://bit.ly/3q0fHgj

Show HN: WikTok – A Recommendation UI for Wikipedia Hi HN, WikTok is a UI for Wikipedia that lets you quickly swipe (or use your arrow keys) to navigate between random and recommended articles (based on the previous articles you interacted most with). It's just a fun project I hacked together this weekend, so may be a little rough around the edges, but I'd love to get your thoughts. Let me know if you have any suggestions (or find any interesting articles!) Cheers, https://bit.ly/3q0vJXD May 22, 2023 at 09:59AM

Show HN: Horizon – Programmatic Prompt Generation and LLM Configurations https://bit.ly/3WqObof

Show HN: Horizon – Programmatic Prompt Generation and LLM Configurations Hi HN. I heard you like dev tools and AI, so we wanted to share our project that we’ve been working on. We’re working on Horizon [1] - a higher level abstraction for LLMs so that developers can spend less time trying to grapple with LLMs to make them work and more time with users. This is the starting feature set which takes an auto-ML approach to identify the optimal LLM model, hyperparameters, and prompt - instead of just giving you the tooling to figure it out yourself. You can read more about it in our documentations. Our view is that as LLMs become increasingly commoditized and prompts become easier to develop all the while fine-tuning is not realistic for the many organization out there - the configuration, optimization, and management will become much more difficult at-scale (consist with Andrej’s recent post [3]). The idea came as we were trying to build LLM apps (think sales outreach, ppt generation, support, etc. etc.) last fall and realized with this tool we could easily build many of the applications with Horizon in minutes versus that days it took us before. Let us know what you think! [1] https://bit.ly/45oesYm [2] https://bit.ly/3WrCXjF [3] https://twitter.com/karpathy/status/1655994367033884672?s=20 https://bit.ly/45oesYm May 22, 2023 at 02:46AM

Show HN: A Simple Load Testing CLI Built in Go https://bit.ly/43gbCCX

Show HN: A Simple Load Testing CLI Built in Go There are plenty of good tools for load testing such as JMeter, Minigun, and plenty more - but they all have their own set of options to learn. I built this one to support a simpler workflow where you just paste your curl request (or other cli command) after your `spam` config (literally just `spam -r 2 -- curl https://bit.ly/43gbD9Z). It's pretty barebones but I'm 100% going to use it in my day to day - figured I'd share it here if it helped anyone else! https://bit.ly/3MNEo8G May 21, 2023 at 08:32PM