Show HN: Searchable Astronomy Picture of the Day https://ift.tt/F9G68Ax

Show HN: Searchable Astronomy Picture of the Day Discover the cosmos by searching the APOD collection, powered by OpenAI text embedding based on the original image descriptions by NASA. https://ift.tt/cY4Ni2z May 26, 2023 at 02:02AM

Show HN: Hacker News in Slow Italian - AI-generated podcast (with code) https://ift.tt/bjpyRmA

Show HN: Hacker News in Slow Italian - AI-generated podcast (with code) There are plenty of podcasts to listen to some slow basic Italian, but often they just talk about random things I'm not that interested in. Nothing a few hours of tinkering with Python cannot solve these days! Introducing Hacker News in Slow Italian. Each episode is generated automatically, using GPT4 API to summarise the top articles on Hacker News and then fed to Play.ht for text-to-speech. The (very short) code is available on Github: https://ift.tt/7vC5ptr https://hn.lingually.ai May 25, 2023 at 10:28PM

Show HN: One-paragraph summaries of the most important news happenings on Earth https://ift.tt/1hLM8PH

Show HN: One-paragraph summaries of the most important news happenings on Earth https://ift.tt/drsAwLP May 26, 2023 at 01:02AM

Show HN: Collaborative recipe manager for iOS, built with SwiftUI and Firebase https://ift.tt/V7KhjFR

Show HN: Collaborative recipe manager for iOS, built with SwiftUI and Firebase I initially created Umami for my family. We'd been using a giant google sheet of recipes that my wife made (one recipe per tab plus a table of contents at the front), but the UX of that left much to be desired, especially on mobile. We also tried a bunch of other recipe apps like Paprika, Whisk, Mela, etc., but most of them don't let you create a shared collection of recipes without using the same login credentials, which we didn't want to share with extended family members. Anyways, I've steadily been working on Umami as a solo side project for about 3 years. At first, just my family and a few friends were using it, but now it's starting to get downloaded by other people. I'd love to get feedback here on what kinds of features would be helpful to y'all. Also happy to answer any questions about the tech stack. Thanks friends! https://ift.tt/BF6c3Rd May 25, 2023 at 11:07PM

Show HN: Course: What Is Outbound Sales Why Is It Important? https://ift.tt/Zr1slRI

Show HN: Course: What Is Outbound Sales Why Is It Important? https://ift.tt/SBfAwXv May 25, 2023 at 02:26PM

Show HN: Create a talent/services marketplace without code https://ift.tt/fiIUwyW

Show HN: Create a talent/services marketplace without code Hi HN We are building a platform that allows anyone to create a custom talent marketplace inside your network. Think of it as Shopify but for talent : ) You can create your own board (store) in minutes, customise and invite your talent. Everything else works our of the box: profiles, matching requests and talent, support, payments, collaboration. The best part is that you make 3-10% every time someone is hired inside your board. You can use it with a link or embed inside your product/community/website. We already have YC startups like Memberstack - https://ift.tt/Of1mtDB among early users. The short backstory: we have originally started Heep as a marketplace for webflow/bubble developers and quickly realised that there are ton of new, niche, emerging professions. So instead of building another talent marketplace we decided to pivot and build a platform to for others to build on top. Our vision is to support any (even the most crazy) emerging talent/services use-cases: if there is a supply and demand for it we wan to help support it. It's currently in early beta and we are looking for feedback and community leaders interested in trying Heep (I will personally onboard you to the product and help you launch your board). Also here for any AMA https://heep.so/?b=yes May 25, 2023 at 04:31AM

Show HN: My word game now has GPT-4 generated poetry https://ift.tt/SW8vGMh

Show HN: My word game now has GPT-4 generated poetry Hi! I just added a new feature to my daily word game https://squareword.org that I though you may find interesting. The game consists of a puzzle of 5x5 letters containing 10 words, that need to be revealed by guessing 5 letter words. Now, once the player has solved the puzzle, they are presented with a poem containing some of these words, generated by GPT-4. Here is an example from a few days ago: https://twitter.com/SquareWordOrg/status/1660702885154377730 While the poems do not always make complete sense and are somewhat whimsical, I am quite impressed by the ability of the model to create an often coherent, rhyming poem from the disparate words. It gives me some extra motivation to solve the daily puzzle! https://squareword.org May 25, 2023 at 03:05AM

Show HN: FarProbe – Access Logic Analyzers from the Browser https://ift.tt/noyERb2

Show HN: FarProbe – Access Logic Analyzers from the Browser FarProbe is a web application that connects to some of the most popular logic analyzers (Saleae, USBee, and their clones) from the browser and streams data to the cloud. Open a Chromium-based browser (even on an Android or ChromeBook), plug in the analyzer, and its data can be streamed over USB to the browser for analysis. After generating a link, the data can be stored on our server or live-streamed to another user. If you don't have the hardware, check out the demo video we prepared for YC over a month ago, we're now live: https://youtu.be/QVoLbB5LAr4 Why did we start it? Often enough I worked on my hardware projects while on the go. Traveling to clients, staying in hotel rooms, I missed a simple tool that allowed me to see what is going on, diagnose it and iterate on the go. I have also seen that problem in the other direction - most recently, I was hybrid-working on electric aircraft avionics, sometimes with the aircraft on the other side of the US. Frequently I had to call some on-site engineers to connect some instruments and screen-share, file-share, send screenshots, etc., to give me a glimpse of the elusive GPS-related bug I was hunting down. What can FarProbe do today? Bare minimum - we like to build in public and want to see where the community needs lead us! You can use a logic analyzer locally, send a link to someone else to capture data for you remotely, you can run long-term acquisitions on our cloud - and export to PulseView for further analysis. You can also invite your colleagues to look at your issue without installing anything new. How does it work? It's a data-intensive WebUSB application written in Rust, both client and server-side. On Linux (Android, Chrome OS) and OSX, we are able to stream ~24MB/s, compress it (most of the time, the signal doesn't change) and send over to our servers. On Windows, we are limited to ~8MB/s, there is a bug in Chromium's WebUSB windows stack that we're thinking about a good way to resolve. What do we want to do in the future? Support more hardware (Oscilloscopes? Any favorite devices you really wished for had better software support?); Implement protocol decoders (also in the cloud); Implement device emulators and test fixtures. Overall - we want to be the software company that gets hardware - and implements the companion software well. https://farprobe.com May 25, 2023 at 02:07AM

Show HN: Mount Unix system into Common Lisp image https://ift.tt/ilhPYD6

Show HN: Mount Unix system into Common Lisp image https://ift.tt/ZTtCSNy May 25, 2023 at 02:04AM

Show HN: I made a Chrome extension to hide history in ChatGPT https://ift.tt/9luZKE1

Show HN: I made a Chrome extension to hide history in ChatGPT https://ift.tt/DVx2gX5 May 24, 2023 at 04:45PM

Show HN: iCal RSVP Helper https://ift.tt/O3n4C6U

Show HN: iCal RSVP Helper Hi HN, We use HEY for Work at my startup, which doesn't have a calendar integration. This is mostly fine, as we can simply use our private calendars, but has a major drawback: We can't reply to invitations in an easy way. I made this microsite to help with this problem until they implement simple Yes/No/Tentative buttons in HEY. It's fully client-side, and gives you the ICS-file you need to attach in an email, and the correct address it needs to be sent to as well - just select your file and RSVP. Hope it's useful for someone else too! https://rsvp.klungo.no/ May 24, 2023 at 12:49PM

Show HN: Defguard – open-source security army knife (Identity,MFA,VPN,Yubikey) https://ift.tt/7zM8cYa

Show HN: Defguard – open-source security army knife (Identity,MFA,VPN,Yubikey) https://ift.tt/FIOm3s5 May 24, 2023 at 03:57PM

Show HN: Dark Mode for HN https://ift.tt/hrVaD3z

Show HN: Dark Mode for HN https://ift.tt/UMjsl8S May 24, 2023 at 02:11PM

Show HN: Honda Civic Infotainment Reverse-Engineering https://ift.tt/85K2e3s

Show HN: Honda Civic Infotainment Reverse-Engineering I own a 2021 Honda Civic and have been annoyed by the lack of public documentation/hacking tools for the Android-based headunit. I hope to address this by publishing my research into the headunit and encouraging discussion and community contribution https://ift.tt/uj3QJvt May 24, 2023 at 06:35AM

Show HN: File-by-file AI-generated comments for your codebase https://ift.tt/jd4uY5V

Show HN: File-by-file AI-generated comments for your codebase My friends and I were complaining about having to decipher incomprehensible code one day and decided to pass the code through GPT to see if it could write easily understandable comments to help us out. It turns out that GPT can but it was still a hassle to generate comments for large files. So we decided to develop a basic web application that automatically integrates with your Github repository, generate comments, create a pull request and send you an email when it is all done. There is definitely a lot more that can be done but we wanted to gain feedback on whether this is a problem that you face too. Do you often find it challenging to understand complex code? Do you have difficulties in writing informative comments? And if so, would you find value in a tool that can automatically generate comments for your code? Really appreciate any feedback and suggestions! Thanks in advance! https://ift.tt/qOrCvlm May 23, 2023 at 07:46PM

Show HN: I'm open sourcing Harmonic, the Android Hacker News client https://ift.tt/ZRXgNBq

Show HN: I'm open sourcing Harmonic, the Android Hacker News client https://ift.tt/eptxbLI May 23, 2023 at 10:26PM

Show HN: I ported my Tetris built with SDL2 to WebAssembly https://ift.tt/jLcZUef

Show HN: I ported my Tetris built with SDL2 to WebAssembly https://ift.tt/r3hltS5 May 23, 2023 at 05:16AM

Show HN: Aimless.js – the missing js randomness library https://ift.tt/akm86CE

Show HN: Aimless.js – the missing js randomness library https://ift.tt/ALdhOic May 23, 2023 at 04:11AM

Show HN: Blotter – An interactive, never ending music video https://ift.tt/b4YuQN2

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://ift.tt/plqH0CG May 23, 2023 at 03:51AM

Show HN: Psychic - An open-source integration platform for unstructured data https://ift.tt/YB8Oymu

Show HN: Psychic - An open-source integration platform for unstructured data My cofounder and I used to work at Robinhood where we shipped the company’s first OAuth integrations, so we know a lot about how data moves between companies. For example, we know that the pain of building new API integrations scales with the level of fragmentation and number of competing "standards". In the current meta, we see this pain with a lot of AI startups who invariably need to connect to their customers data, but have to support 50+ integrations before they even scale to 50+ customers. This is the process for an AI startup to add a new integration for a customer: - Pore over the API docs for each source application and write a connector for each - Play email tag to find the right stakeholders and get them to share sensitive API keys, or give them an OAuth app. It can take 6+ weeks for some platforms to review new OAuth apps - Normalize data that arrives in a different formats from each source (HTML, XML, text dumps, 3 different flavors of markdown, JSON, etc) - Figure out what data should be vectorized, what should be stored as SQL, and what should be discarded - Detect when data has been updated and synchronize it - Monitor when pipelines break so data doesn’t go stale This is a LOT of work for something that doesn’t move the needle on product quality. That’s why we built Psychic.dev to be the fastest and most secure way for startups to connect to their customer’s data. You integrate once with our universal APIs and get N integrations with CRMs, knowledge bases, ticketing systems and more with no incremental engineering effort. We abstract away the quirks of each data source into Document and Conversation data models, and try to find a good balance to allow for deep integrations while maintaining broad utility. Since it’s open source, we encourage founders to fork and extend our data models to fit their needs as they evolve, even if it means migrating off our paid version. To see an example in action, check out our demo repo here: https://ift.tt/rUA8Sne We are also open source and open to contributions, learn more at docs.psychic.dev or by emailing us at founders@psychic.dev! https://ift.tt/9UmOVCy May 22, 2023 at 08:11PM