Show HN: ParallelGPT – Batch processing with ChatGPT on low-code spreadsheet UI https://ift.tt/o3DTKbf

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/REK1P0W... 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/TnjXbWx April 1, 2023 at 06:17AM

Show HN: Simply explain 20k concepts using GPT https://ift.tt/avzweuy

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/ItKXifT April 1, 2023 at 03:54AM

Show HN: Cadseer. a parametric solid modeling CAD desktop application https://ift.tt/mFuzh0i

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/rUJVyEc April 1, 2023 at 12:05AM

Show HN: Multi-Display Screen Sharing with CoScreen by Datadog https://ift.tt/R79S8AO

Show HN: Multi-Display Screen Sharing with CoScreen by Datadog Good to be back on HN with all-new CoScreen, a little more than 3 years after it launched over here! With CoScreen 5.0, you can now share your windows from multiple displays at the same time, a long standing request by our most avid users and impossible in other apps. It also has a lightning-fast, Rust-based window compositing, scaling, and streaming engine now. CoScreen was always meant to be different so that you and your team can share your screens simultaneously and multi-directionally, and to be able to control what is being shared. We saw it as a natural extension and closely coupled with your OS — instant, fast, and seamless. A better way to pair program, debug tough incidents, or jam on great ideas by sharing multi-modal information like code, commands, graphs, or logs. All that made a lot of sense conceptually but to be frank, it was hard to get it right. Now a part of Datadog and with major parts of our app rewritten in Rust, we feel we’re closer than ever. Here’s what pair programmers liked about CoScreen, so we made it even better: - High definition code sharing: Windows are video-streamed in real-time at their native resolution whenever possible. You never have to search for your IDE anymore or be anxious to share the wrong window. - Multi-directional collaboration: You can share, while Alice shares, while Bob shares. Side-by-side, across multiple displays. With built-in crisp audio and video chat. - 60FPS+ super smooth mouse pointers. Type, click, and draw on any shared window as if it was your own. What some of you did NOT like, so we fixed it in CoScreen V5: - CPU utilization and latency have been reduced drastically as various parts of our desktop client are now implemented in Rust, building on crates such as cxx, rust-skia, iced, as well as Neon for our native remote control plugins. - No more accidental clicking into remote windows through the new remote window toggles. - You’re no longer bound by your displays, can share windows from multiple of them at the same time and even move them across displays while sharing without stopping. - You’ll also soon be able to join meetings from your browser from any platform. CoScreen runs on macOS (x64 and Apple Silicon), Windows, soon also on the web and is currently free. We’re planning to charge for larger teams and enterprise features in the future. Hopefully - finally - we’ll also have a Linux version one day. Tell us if you need it urgently and if you have any other requirements! https://ift.tt/BOv6pPr March 31, 2023 at 07:21PM

Show HN: Random Aerial Airport Views https://ift.tt/W7JQRvg

Show HN: Random Aerial Airport Views Hi HN! Sharing Random Airport Inspired by RandomStreetView (which I find weirdly addictive), and a passion for air travel. Probably not for everyone, but I hope some of you find it interesting! Needless to say, open to feedback! Enjoy clicking! Further reading: TECH: It's Build in React, NodeJS, with a Notion DB. The code is public on Github. It is spaghetti though ... Especially open to feedback here. DB: The db is publicly available (and editable), I can add the link in comments if anyone would like to have a look . KNOWN ISSUES: I would like to improve the design, pic loading performance and quality of (some) pics. https://ift.tt/3PBqbo9 March 31, 2023 at 10:27AM

Show HN: Free Online Screen Recorder MP4 and WEBM https://ift.tt/kJqLUfl

Show HN: Free Online Screen Recorder MP4 and WEBM https://ift.tt/YgWfDUE March 30, 2023 at 05:04PM

Show HN: The AI Manifesto for Humanity https://ift.tt/w2ZD5OP

Show HN: The AI Manifesto for Humanity see comments https://ift.tt/O91f7Sb March 30, 2023 at 04:22PM

Show HN: Yesterday I open sourced StratusGFX, a realtime 3D rendering engine https://ift.tt/JqVrLHB

Show HN: Yesterday I open sourced StratusGFX, a realtime 3D rendering engine It's been closed source for a long time while I worked on it on and off as a hobby research project, but yesterday the repo was made public for the first time under the MPL 2.0 license. A feature reel showing its capabilities can be found here: https://ift.tt/hEYa9wJ... A technical breakdown of a single frame can be found here: https://ift.tt/hTyG02x... It's still in a very beta state (bugs and instability expected), but I felt like it was a good time to make it public since a lot of its core features are mostly presentable. I plan to continue working on it in my spare time to try and improve the usability of the code. Two main use cases I could see for it: 1) People using it for educational purposes. 2) People integrating it into other more general purpose engines that they're working on since Stratus is primarily a rendering engine. Any extensions to the rendering code that are made public would then further help others. So I think it will remain very niche but I'm hoping it will still be helpful for people in the future. https://ift.tt/mQtU1lV March 30, 2023 at 03:25PM

Show HN: Sendsecurely.io – an audited secure file sharing platform https://ift.tt/JANojPt

Show HN: Sendsecurely.io – an audited secure file sharing platform Hi HN! tldr: SendSecurely is a secure platform to send sensitive documents and files to others. All files are encrypted locally before uploading to SendSecurely. The decryption keys are also encrypted and managed by a new audited database system. Anytime anyone accesses the decrypted keys, an audit log is created letting you keep track of everyone you have shared the file with and when they have accessed it. We would love for you to try this new system and share feedback! long (and technical) story: My partner and I have been working for the past 2 years on building a new privacy-oriented database system called EthicalDB. EthicalDB utilizes blockchain technology to codify both database schema and database permissions. All data in EthicalDB must be associated with an entity in the database and predefined by the schema as public or private data. Permissions are also defined in the schema. Private data is stored encrypted within EthicalDB in a special way that requires multiple nodes to provide decryption keys to access the private data. This forms the basis of governance and accountability in the system such that no one node can access the private data. For private data to be accessed, a private data request must be submitted to the blockchain ledger from an entity existing within EthicalDB. The nodes validate that the entity has permission to access the requested private data and then submit decryption keys for the entity to be able to access the data. In this way, there is no separation between data access and audit - you must submit a data request to get access to the data. We view this radically different architecture and design from traditional database systems as necessary if we wish to codify privacy policies and truly have support for individual personal data ownership and protection. After a combined 25 years working as internet application developers, my partner Travis and I saw that database systems sucked at storing personal data and any attempt to do so was an afterthought. Core problem: every database system is designed assuming the hosting organization has full ownership of all the data within the system. We asked ourselves what would a database system look like if a system was designed from the ground up to respect privacy and personal data ownership? - EthicalDB is what resulted. There are many uses we can see for EthicalDB, but one of the first applications we felt comfortable building and releasing to the public is a secure file sharing platform. We would love input and feedback on SendSecurely! We'd be also happy to discuss with anyone interested a technical deep dive on the EthicalDB technology. Thanks for checking this out! https://ift.tt/of7jVli March 30, 2023 at 09:50AM

Show HN: Type Safe SQL Query Builder https://ift.tt/RQf6lLp

Show HN: Type Safe SQL Query Builder https://kysely.dev/ March 30, 2023 at 08:58AM

Show HN: Marvin – build AI functions that use an LLM as a runtime https://ift.tt/yZzXu8Q

Show HN: Marvin – build AI functions that use an LLM as a runtime Hey HN! We're excited to share our new open-source project, Marvin. Marvin is a high-level library for building AI-powered software. We developed it to address the challenges of integrating LLMs into more traditional applications. One of the biggest issues is the fact that LLMs only deal with strings (and conversational strings at that), so using them to process structured data is especially difficult. Marvin introduces a new concept called AI Functions. These look and feel just like regular Python functions: you provide typed inputs, outputs, and docstrings. However, instead of relying on traditional source code, AI functions use LLMs like GPT-4 as a sort of “runtime” to generate outputs on-demand, based on the provided inputs and other details. The results are then parsed and converted back into native data types. This “functional prompt engineering” means you can seamlessly integrate AI functions with your existing codebase. You can chain them together with other functions to form sophisticated, AI-enabled pipelines. They’re particularly useful for tasks that are simple to describe yet challenging to code, such as entity extraction, semantic scraping, complex filtering, template-based data generation, and categorization. For example, you could extract terms from a contract as JSON, scrape websites for quotes that support an idea, or build a list of questions from a customer support request. All of these would yield structured data that you could immediately start to process. We initially created Marvin to tackle broad internal use cases in customer service and knowledge synthesis. AI Functions are just a piece of that, but have proven to be even more effective than we anticipated, and have quickly become one of our favorite features! We’re eager for you to try them out for yourself. We’d love to hear your thoughts, feedback, and any creative ways you could use Marvin in your own projects. Let’s discuss in the comments! https://ift.tt/wd2mjUW March 30, 2023 at 07:34AM

Show HN: SpamZappr – AI-Powered Spam Detection Solution https://ift.tt/SnWMguq

Show HN: SpamZappr – AI-Powered Spam Detection Solution If you're looking for a cutting-edge solution to keep spam at bay and create a cleaner online space, then look no further than SpamZappr! Our AI-powered spam detection tool will revolutionize the way you manage spam in your online community. Spam is an ever-present issue in the digital world, and it can be a frustrating and time-consuming problem for anyone trying to manage an online community. That's why we created SpamZappr, a powerful tool designed to effortlessly detect and filter spam with AI technology. Our goal with SpamZappr is to make managing online communities easier and more enjoyable for everyone. With our tool, you can protect your users from malicious content, improve user engagement, and maintain a professional online presence. What's more, we've made it incredibly easy to integrate SpamZappr into your existing platform or application. Our developer-friendly API lets you quickly implement spam detection, so you can focus on what really matters: building a strong and engaged community. https://spamzappr.com March 30, 2023 at 05:51AM

Show HN: Hacker News Summarizer (Chrome Extension) https://ift.tt/feCYVz0

Show HN: Hacker News Summarizer (Chrome Extension) Hey Hacker News community, We're excited to announce the launch of our new Chrome extension, "Hacker News Summarizer," which uses OpenAI API to summarize articles on Hacker News. It helps you quickly understand the key takeaways without reading the whole article. Plus, no login or confirmation is required to use it! Simply install the extension and click the "summary" link next to "comments" when you want to read an article. Disclaimer: Not all articles are summarised, or supported but we will change and try to support them later. Additionally, this extension is not affiliated with OpenAI or Hacker News. Chrome Extension: https://ift.tt/0RzjN3W ... Try it out today and let us know what you think in the comments below! Thanks, The Hacker News Summarizer team https://ift.tt/G0LDNTo March 29, 2023 at 04:18PM

Show HN: GPT-3.5-turbo wrapped inside my personal website https://ift.tt/JqrZXVW

Show HN: GPT-3.5-turbo wrapped inside my personal website https://ift.tt/mTqV31J March 29, 2023 at 03:04PM

Show HN: Atmos – Everything you need to create color palettes https://ift.tt/LvoxtrQ

Show HN: Atmos – Everything you need to create color palettes https://atmos.style March 29, 2023 at 01:08PM

Show HN: Tampermonkey userscript for removing HN threads via predefined regexes https://ift.tt/GxnEUSd

Show HN: Tampermonkey userscript for removing HN threads via predefined regexes https://ift.tt/LX625hf March 29, 2023 at 09:15AM

Show HN: Customizable, embeddable Chat GPT based on your own documents https://ift.tt/gLzBsNp

Show HN: Customizable, embeddable Chat GPT based on your own documents https://libraria.dev/ March 29, 2023 at 06:41AM

Show HN: Call Gen Z GPT 1-650-729-9536 Built with Vocode (YC W23) and Rime TTS https://ift.tt/m9rC1T4

Show HN: Call Gen Z GPT 1-650-729-9536 Built with Vocode (YC W23) and Rime TTS Hey HN! Try calling: +16507299536 to talk to Gen Z GPT. This a quick demo of what you can do with Vocode (open source toolkit for building voice-based LLM applications). We've collaborated with Rime using their text-to-speech for this demo! https://ift.tt/M9QWSiG March 29, 2023 at 02:21AM

Show HN: GPT4 vs. GPT3:What you should know https://ift.tt/7OlhxTU

Show HN: GPT4 vs. GPT3:What you should know https://ift.tt/42MHgf7 March 28, 2023 at 08:22PM

Show HN: DiskerNet – save and index web content locally https://ift.tt/Qv1JR5S

Show HN: DiskerNet – save and index web content locally https://ift.tt/ylUNEkD March 28, 2023 at 05:32PM