Show HN: Ente Authenticator – open-source 2FA app with e2ee backups
4 by vishnumohandas | 3 comments on Hacker News.
Sunday, 30 April 2023
New Show Hacker News story: latest news
Show HN: Frogmouth – A Markdown browser for your terminal
3 by willm | 0 comments on Hacker News.
Hi HN, Frogmouth is a TUI to display Markdown files. It does a passable job of displaying Markdown, with code blocks and tables. No image support as yet. It's very browser like, with navigation stack, history, and bookmarks. Works with both the mouse and keyboard. There are shortcuts for viewing README.md files and other Markdown on GitHub and GitLab. License is MIT. Let me know what you think...
3 by willm | 0 comments on Hacker News.
Hi HN, Frogmouth is a TUI to display Markdown files. It does a passable job of displaying Markdown, with code blocks and tables. No image support as yet. It's very browser like, with navigation stack, history, and bookmarks. Works with both the mouse and keyboard. There are shortcuts for viewing README.md files and other Markdown on GitHub and GitLab. License is MIT. Let me know what you think...
New Show Hacker News story: latest news
Show HN: What The Element? Learn the name of chemical elements
2 by jazzsouff | 0 comments on Hacker News.
Hello HN! I am sharing with you my first newbie project. You basically click on a chemical symbol and try to guess the name. You can play in English or French. I made it in a week during a bootcamp I am attending. It's not perfect but I tried my best. I am looking forward to some feedback or code review to improve upon it :) Enjoy
2 by jazzsouff | 0 comments on Hacker News.
Hello HN! I am sharing with you my first newbie project. You basically click on a chemical symbol and try to guess the name. You can play in English or French. I made it in a week during a bootcamp I am attending. It's not perfect but I tried my best. I am looking forward to some feedback or code review to improve upon it :) Enjoy
New Show Hacker News story: latest news
Show HN: Browser-based robot simulator with Three.js and rapier.js
3 by coolvision | 0 comments on Hacker News.
3 by coolvision | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: ArchitectGPT – AI Powered Home Design Too
2 by britok30 | 1 comments on Hacker News.
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.
2 by britok30 | 1 comments on Hacker News.
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.
Saturday, 29 April 2023
New Show Hacker News story: latest news
Show HN: Open-Source Implementation of John Conway's Mathy Game of Hackenbush
2 by fi-le | 0 comments on Hacker News.
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.
2 by fi-le | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: A Gentle Introduction to the Fediverse
6 by ftfish | 0 comments on Hacker News.
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.
6 by ftfish | 0 comments on Hacker News.
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.
Friday, 28 April 2023
New Show Hacker News story: latest news
Show HN: Make 3D printable CAD Models with GPT
2 by mitchecu | 0 comments on Hacker News.
Create 3D models just using your words. This project turns text-to-3d with OpenSCAD as an intermediary.
2 by mitchecu | 0 comments on Hacker News.
Create 3D models just using your words. This project turns text-to-3d with OpenSCAD as an intermediary.
New Show Hacker News story: latest news
Show HN: I made a tool to easily credit co-contributors in Git commits
2 by prollyjethi | 0 comments on Hacker News.
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.
2 by prollyjethi | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: ChatGPT Plugin that semantically searches Google Maps
2 by sdan | 0 comments on Hacker News.
2 by sdan | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: Use Terraform Modules in Pulumi
4 by Randomdevops | 0 comments on Hacker News.
Use your battle-tested or 3rd party Terraform modules directly in your Pulumi workflow.
4 by Randomdevops | 0 comments on Hacker News.
Use your battle-tested or 3rd party Terraform modules directly in your Pulumi workflow.
New Show Hacker News story: latest news
Show HN: Jarvis AI – Text, iMessage, and Email ChatGPT
2 by khalidx | 0 comments on Hacker News.
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/JxPsgqS
2 by khalidx | 0 comments on Hacker News.
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/JxPsgqS
New Show Hacker News story: latest news
Show HN: Code-Narrator: Automating Documentation with GPT-4
2 by ingigauti | 0 comments on Hacker News.
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/KBAOlq7 ) 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/HwdQNMK... . 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!
2 by ingigauti | 0 comments on Hacker News.
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/KBAOlq7 ) 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/HwdQNMK... . 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!
Thursday, 27 April 2023
New Show Hacker News story: latest news
Show HN: ScrapScript – A tiny functional language for sharable software
6 by surprisetalk | 0 comments on Hacker News.
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 :)
6 by surprisetalk | 0 comments on Hacker News.
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 :)
New Show Hacker News story: latest news
Show HN: Codeium-Chrome: Free open-source AI autocomplete Chrome extension
2 by varunkmohan | 0 comments on Hacker News.
2 by varunkmohan | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: A Bel compiler to Emacs Lisp bytecode
4 by restif1975 | 0 comments on Hacker News.
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.
4 by restif1975 | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: Karrio – Open-Source Multi-Carrier Shipping API
6 by dan91 | 0 comments on Hacker News.
Hey HN! Daniel and Delali here; we are working on Karrio, an open-source shipping infrastructure. Our focus is on making it easy to integrate shipping into platforms. With Karrio’s open-source and universal shipping API, you can set up connections to a worldwide network of shipping carriers for national, international and last-mile services but also build your own network of local carriers. You can seamlessly add built-in shipping functionalities to your platform, enabling users to fetch live rates, buy labels, track packages, and more. You can check out our Github repo here: https://ift.tt/32RIZdL . For developers in the logistics space, carrier integration is often a painful experience. We believe that an open-source solution is a viable alternative to building a shipping system from scratch in-house or getting locked in with a Saas multi-carrier API. Karrio aims to put you in control of your shipping network with lower engineering costs. (see how to get started here: https://ift.tt/AY0Ekeq ). So far, we’ve built a unified shipping API compatible with most major carriers, such as FedEx, UPS, DHL, USPS, Canada Post, and more. With the flexibility of open-source, Karrio has interoperability with other multi-carriers and 3PL (EasyPost, Freightcom, etc.). And we plan on building more integrations. Karrio is evolving with the help of our community of early adopters, and we want to keep that going. Checkout our README to get involved with the project, file issues and request or contribute carrier integrations We currently offer a managed cloud service in private beta, with a pay-as-you-go plan for platforms and custom prices for enterprise customers. Don’t hesitate to reach out if you have any questions. We would love to hear your feedback and how Karrio can help with your project.
6 by dan91 | 0 comments on Hacker News.
Hey HN! Daniel and Delali here; we are working on Karrio, an open-source shipping infrastructure. Our focus is on making it easy to integrate shipping into platforms. With Karrio’s open-source and universal shipping API, you can set up connections to a worldwide network of shipping carriers for national, international and last-mile services but also build your own network of local carriers. You can seamlessly add built-in shipping functionalities to your platform, enabling users to fetch live rates, buy labels, track packages, and more. You can check out our Github repo here: https://ift.tt/32RIZdL . For developers in the logistics space, carrier integration is often a painful experience. We believe that an open-source solution is a viable alternative to building a shipping system from scratch in-house or getting locked in with a Saas multi-carrier API. Karrio aims to put you in control of your shipping network with lower engineering costs. (see how to get started here: https://ift.tt/AY0Ekeq ). So far, we’ve built a unified shipping API compatible with most major carriers, such as FedEx, UPS, DHL, USPS, Canada Post, and more. With the flexibility of open-source, Karrio has interoperability with other multi-carriers and 3PL (EasyPost, Freightcom, etc.). And we plan on building more integrations. Karrio is evolving with the help of our community of early adopters, and we want to keep that going. Checkout our README to get involved with the project, file issues and request or contribute carrier integrations We currently offer a managed cloud service in private beta, with a pay-as-you-go plan for platforms and custom prices for enterprise customers. Don’t hesitate to reach out if you have any questions. We would love to hear your feedback and how Karrio can help with your project.
New Show Hacker News story: latest news
Show HN: GraphAr – An Open-Source File Format for Graph Data Archive/Exchange
5 by bryaneno | 0 comments on Hacker News.
Hi, Hacker News! We're excited to announce the release of GraphAr, an open-source file format for archiving and exchanging graph data. The landscape of graph processing systems is fragmented, with various types of systems, including graph databases, graph computation systems, and GNN systems. However, currently, there is no common file format for efficiently storing and exchanging graph data while maintaining its schema and graph semantics. GraphAr is designed to address this issue by providing a simple, lightweight format for storing and exchanging graph data. GraphAr is a flexible and adaptable format that can be used across a variety of applications by decoupling the storage of metadata, adjacency, and properties. It is also designed to be efficient by leveraging existing formats such as ORC, Parquet, and CSV as much as possible. This makes it easy to integrate with existing data processing systems and provides a level of familiarity for users. Furthermore, GraphAr preserves the semantics of graphs and can maintain the schema of property graphs. This means that users can maintain the same graph structure across different systems, ensuring that the graph's semantics are not lost. We have developed both a C++ library for accessing and creating GraphAr files, and a Spark library for transforming data into and from GraphAr files. With these libraries, it's easy to work with GraphAr files in your existing Spark connectors or C++ projects. As GraphAr matures, we aim to move the project to a vendor-neutral venue, such as Apache, LF AI & Data. This will ensure that the project continues to be developed in an open and transparent manner, with contributions from a broad community of developers. To get started with GraphAr, check out our GitHub repository, where you'll find detailed documentation and examples of how to use the libraries. We welcome any feedback or contributions to the project. Let's make graph data archiving and exchange more efficient with GraphAr!
5 by bryaneno | 0 comments on Hacker News.
Hi, Hacker News! We're excited to announce the release of GraphAr, an open-source file format for archiving and exchanging graph data. The landscape of graph processing systems is fragmented, with various types of systems, including graph databases, graph computation systems, and GNN systems. However, currently, there is no common file format for efficiently storing and exchanging graph data while maintaining its schema and graph semantics. GraphAr is designed to address this issue by providing a simple, lightweight format for storing and exchanging graph data. GraphAr is a flexible and adaptable format that can be used across a variety of applications by decoupling the storage of metadata, adjacency, and properties. It is also designed to be efficient by leveraging existing formats such as ORC, Parquet, and CSV as much as possible. This makes it easy to integrate with existing data processing systems and provides a level of familiarity for users. Furthermore, GraphAr preserves the semantics of graphs and can maintain the schema of property graphs. This means that users can maintain the same graph structure across different systems, ensuring that the graph's semantics are not lost. We have developed both a C++ library for accessing and creating GraphAr files, and a Spark library for transforming data into and from GraphAr files. With these libraries, it's easy to work with GraphAr files in your existing Spark connectors or C++ projects. As GraphAr matures, we aim to move the project to a vendor-neutral venue, such as Apache, LF AI & Data. This will ensure that the project continues to be developed in an open and transparent manner, with contributions from a broad community of developers. To get started with GraphAr, check out our GitHub repository, where you'll find detailed documentation and examples of how to use the libraries. We welcome any feedback or contributions to the project. Let's make graph data archiving and exchange more efficient with GraphAr!
New Show Hacker News story: latest news
Show HN: E2EE iOS Keyboard Calendar Built in React Native
4 by mfbx9da4 | 0 comments on Hacker News.
4 by mfbx9da4 | 0 comments on Hacker News.
Wednesday, 26 April 2023
New Show Hacker News story: latest news
Show HN: Retro games hosted in Cloudflare Pages for free
7 by technicidat | 0 comments on Hacker News.
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.
7 by technicidat | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: Parley: The RPG where you Negotiate with Bandits
2 by upwardbound | 0 comments on Hacker News.
2 by upwardbound | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: Using object detection to turn a webcam into a lightgun
2 by aliraheem | 0 comments on Hacker News.
A rather silly project that uses a Coral.ai edgeTPU mini PCIe board to detect a monitor in a webcam feed and convert that into either mouse movements or joystick input. There's a video in the repository showing the gameplay[0]. [0] https://www.youtube.com/watch?v=7g3i7UJV5Zg and in the repository.
2 by aliraheem | 0 comments on Hacker News.
A rather silly project that uses a Coral.ai edgeTPU mini PCIe board to detect a monitor in a webcam feed and convert that into either mouse movements or joystick input. There's a video in the repository showing the gameplay[0]. [0] https://www.youtube.com/watch?v=7g3i7UJV5Zg and in the repository.
New Show Hacker News story: latest news
Show HN: I'm working on an open source writing app
4 by egonschiele | 3 comments on Hacker News.
Hey Hacker News, I'm a writer who sometimes misses the fancy features of a code editor, so I started building Chisel. What can Chisel do? - Command palette like VSCode - Git-like history to keep track of your writing journey - Writing feedback ala Hemingway or Grammarly - And it even integrates with ChatGPT I've tried out some other apps like Bear and Obsidian, but Chisel has been a better fit. It's more about writing and less about note-taking. Head over to https://ift.tt/Q6Wznl0 to check it out!
4 by egonschiele | 3 comments on Hacker News.
Hey Hacker News, I'm a writer who sometimes misses the fancy features of a code editor, so I started building Chisel. What can Chisel do? - Command palette like VSCode - Git-like history to keep track of your writing journey - Writing feedback ala Hemingway or Grammarly - And it even integrates with ChatGPT I've tried out some other apps like Bear and Obsidian, but Chisel has been a better fit. It's more about writing and less about note-taking. Head over to https://ift.tt/Q6Wznl0 to check it out!
New Show Hacker News story: latest news
Show HN: An interactive map showing live wind farm generation in Great Britain
12 by robhawkes | 3 comments on Hacker News.
GB Renewables Map an energy experiment created entirely in my free time (day job is visualisation at Octopus Energy). It's an interactive map showing live generation for major wind farms in Great Britain, showing what each wind farm is generating both now and in the past, and where that generation is physically located. Animated weather data is from WeatherLayers and shows current and historic wind conditions on the map, providing context to wind generation around the country. History mode allows you to go back in time and see wind generation and weather conditions for a particular date and time. It's great for exploring days of record generation, such as the 21.6GW record on January 10th, 2023! Prediction mode lets you see what wind farms are estimated to be generating using current wind conditions and model based on historic generation and wind speeds. Is a wind farm generating as you expect, or is there something to look into? An experimental feature allows you to see what future wind farms could be generating today (or in the past!) if they were already built and operational. If you click the "sparkle" button on the map you'll get to see what the upcoming 3.6GW Dogger Bank wind farm is estimated to generate if it was operational today. There's an "About" section on the site that goes into detail on the various public data sources and how some of the features work. I also document a lot of this on my Twitter @robhawkes if you're curious. This is just the start and there are many more features to come! Please let me know your comments and suggestions.
12 by robhawkes | 3 comments on Hacker News.
GB Renewables Map an energy experiment created entirely in my free time (day job is visualisation at Octopus Energy). It's an interactive map showing live generation for major wind farms in Great Britain, showing what each wind farm is generating both now and in the past, and where that generation is physically located. Animated weather data is from WeatherLayers and shows current and historic wind conditions on the map, providing context to wind generation around the country. History mode allows you to go back in time and see wind generation and weather conditions for a particular date and time. It's great for exploring days of record generation, such as the 21.6GW record on January 10th, 2023! Prediction mode lets you see what wind farms are estimated to be generating using current wind conditions and model based on historic generation and wind speeds. Is a wind farm generating as you expect, or is there something to look into? An experimental feature allows you to see what future wind farms could be generating today (or in the past!) if they were already built and operational. If you click the "sparkle" button on the map you'll get to see what the upcoming 3.6GW Dogger Bank wind farm is estimated to generate if it was operational today. There's an "About" section on the site that goes into detail on the various public data sources and how some of the features work. I also document a lot of this on my Twitter @robhawkes if you're curious. This is just the start and there are many more features to come! Please let me know your comments and suggestions.
Tuesday, 25 April 2023
New Show Hacker News story: latest news
Show HN: Introducing Palacio Albums – Create, Share and Explore Photo Albums
2 by nikhil333 | 0 comments on Hacker News.
2 by nikhil333 | 0 comments on Hacker News.
New Show Hacker News story: latest news
A command-line tool to easily kill processes running on a specified port
116 by jkfran | 118 comments on Hacker News.
116 by jkfran | 118 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: TravelGPT Adventures: Your Guide to Experiencing the World with GPT
4 by relatedcode | 3 comments on Hacker News.
4 by relatedcode | 3 comments on Hacker News.
Monday, 24 April 2023
New Show Hacker News story: latest news
Show HN: Feed of random Wikipedia articles (mobile friendly)
2 by Zakuzaa | 1 comments on Hacker News.
2 by Zakuzaa | 1 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: A C++ web/application framework I have been building for the last 12yrs
2 by sumeetchhetri | 0 comments on Hacker News.
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.
2 by sumeetchhetri | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: I quit my job to build a Kubernetes GUI with Rust
3 by goenning | 0 comments on Hacker News.
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!
3 by goenning | 0 comments on Hacker News.
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!
New Show Hacker News story: latest news
Show HN: Q&A Bot talking in Hinglish about PDFs
9 by deepankarm44 | 0 comments on Hacker News.
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
9 by deepankarm44 | 0 comments on Hacker News.
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
Sunday, 23 April 2023
New Show Hacker News story: latest news
Show HN: ChatGPT-Powered AI Girlfriend App – Experience the Future of Romance
4 by thyselius | 1 comments on Hacker News.
4 by thyselius | 1 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: I was frustrated with pricing of PagerDuty et al., so made it myself
3 by mads_quist | 0 comments on Hacker News.
3 by mads_quist | 0 comments on Hacker News.
Saturday, 22 April 2023
New Show Hacker News story: latest news
Show HN: I designed and coded my portfolio as a freelance designer
2 by edgarasben | 0 comments on Hacker News.
Feel free to share any feedback. Thank you.
2 by edgarasben | 0 comments on Hacker News.
Feel free to share any feedback. Thank you.
New Show Hacker News story: latest news
Show HN: I made an automated phishing email analysis tool called ThePhish
2 by emalderson | 2 comments on Hacker News.
It's based on TheHive, Cortex and MISP. I'll update it once the new TheHive API 5 will be released as stable.
2 by emalderson | 2 comments on Hacker News.
It's based on TheHive, Cortex and MISP. I'll update it once the new TheHive API 5 will be released as stable.
New Show Hacker News story: latest news
Show HN: Layoff Runbook for engineers who have been let go
2 by derwiki | 0 comments on Hacker News.
2 by derwiki | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: I made a website with musical exercises for beginner musicians
2 by jessym | 1 comments on Hacker News.
2 by jessym | 1 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: I made a SQL game to help people learn / challenge their skills
16 by robinLord | 0 comments on Hacker News.
16 by robinLord | 0 comments on Hacker News.
Friday, 21 April 2023
New Show Hacker News story: latest news
Show HN: Stadai – Your virtual study buddy powered by ChatGPT
4 by hacker79 | 0 comments on Hacker News.
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!
4 by hacker79 | 0 comments on Hacker News.
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!
New Show Hacker News story: latest news
Show HN: ChatGPT-powered Search Bar for your Site
2 by parthi | 0 comments on Hacker News.
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.
2 by parthi | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: Build AI DAGs with Memory; Run and Validate LLM Tools in Containers
3 by vasinov | 2 comments on Hacker News.
I am working on a modular open source framework called Griptape that allows Python developers to create LLM pipelines and DAGs for complex workflows that use rules and memory. Griptape can be thought of as "Airflow for LLMs," providing an alternative to the agent-based LangChain approach. Developers can also build reusable LLM tools with explicit JSON schemas that can be executed in any environment (local, containerized, cloud, etc.) and integrated into Griptape workflows. They can also be easily converted into ChatGPT Plugin APIs and LangChain tools via adapters. Tools can be thought of as any executable code that allows LLMs to interact with the outside world (via ReAct and Toolformer techniques): email, docs, spreadsheets, Jira tickets, web pages/search, etc. The best part about tools is that they can be executed in isolated environments, significantly reducing potential security risks associated with running LLM-generated code and API calls. What do you think? What are some of the use cases that you have in mind for reusable tools?
3 by vasinov | 2 comments on Hacker News.
I am working on a modular open source framework called Griptape that allows Python developers to create LLM pipelines and DAGs for complex workflows that use rules and memory. Griptape can be thought of as "Airflow for LLMs," providing an alternative to the agent-based LangChain approach. Developers can also build reusable LLM tools with explicit JSON schemas that can be executed in any environment (local, containerized, cloud, etc.) and integrated into Griptape workflows. They can also be easily converted into ChatGPT Plugin APIs and LangChain tools via adapters. Tools can be thought of as any executable code that allows LLMs to interact with the outside world (via ReAct and Toolformer techniques): email, docs, spreadsheets, Jira tickets, web pages/search, etc. The best part about tools is that they can be executed in isolated environments, significantly reducing potential security risks associated with running LLM-generated code and API calls. What do you think? What are some of the use cases that you have in mind for reusable tools?
New Show Hacker News story: latest news
Show HN: Bend (YC S22) A climate-friendly corporate card ($100 to try it)
17 by tedpower | 9 comments on Hacker News.
Hi HN! We’re Ted and Thomas from Bend (YC S22). Today we’re launching a modern corporate card built for climate-friendly business. Just by shifting some of your company spending to Bend, you’ll be helping to reduce climate-changing emissions, thanks to the carbon removal rewards you’ll automatically earn, and our embedded climate analytics. But we know that signing up for a new financial service can take some upfront effort, so we wanted to sweeten the deal — create an account today (Friday Apr 21), and we’ll deposit a *$100 gift* in your account to start spending immediately — see the site for details. How it works: - Bend is a modern card and cash account, combined with free carbon accounting and climate rewards - Bend works similarly to how you’d use a business bank account. Send and receive ACH and wires, earn 3% yield on deposits, issue physical and virtual cards with budgets, etc. - Carbon accounting typically runs companies $40k/year and up. We make money off the card interchange (same as any bank), enabling us to offer the carbon accounting for free, and pass through carbon removal rewards. - The way we actually do the carbon accounting is laid out here — we always return a confidence score with every CO2e assessment: https://ift.tt/mwXv5LG - We have awesome customers like Harmonic AI https://ift.tt/JPgZko3 and Fathom https://ift.tt/Ya910Pj . If you choose, you can create a report of your climate action through Bend like these ones, which you can share with customers, employees, investors, etc. Why tracking and reducing climate-changing emissions is worthwhile: - It’s good for the planet (and free!) - It will help you sell your products to B2C customers who care about the climate, and B2B customers who have set net zero goals (64% of global market cap companies now report on climate data, and are increasingly asking their suppliers to do the same) Our stack: - Rust back end - NextJS front end - Hosted on Vercel - Database from PlanetScale - Card issuing and treasury powered by Stripe and partner banks - Charts with Visx How we got here: We launched Bend last summer as an API https://ift.tt/J470zED . We’re now launching cards directly, because we’re able to offer the functionality for free, and it’s easier for startups to try it out. Prior to Bend, Thomas and I worked at Abacus, where I was one of the co-founders https://ift.tt/Ci32xlY — our background is in fintech, and our goal is to layer in climate insights on top of your financial stack. We’d love it if you tried Bend out!
17 by tedpower | 9 comments on Hacker News.
Hi HN! We’re Ted and Thomas from Bend (YC S22). Today we’re launching a modern corporate card built for climate-friendly business. Just by shifting some of your company spending to Bend, you’ll be helping to reduce climate-changing emissions, thanks to the carbon removal rewards you’ll automatically earn, and our embedded climate analytics. But we know that signing up for a new financial service can take some upfront effort, so we wanted to sweeten the deal — create an account today (Friday Apr 21), and we’ll deposit a *$100 gift* in your account to start spending immediately — see the site for details. How it works: - Bend is a modern card and cash account, combined with free carbon accounting and climate rewards - Bend works similarly to how you’d use a business bank account. Send and receive ACH and wires, earn 3% yield on deposits, issue physical and virtual cards with budgets, etc. - Carbon accounting typically runs companies $40k/year and up. We make money off the card interchange (same as any bank), enabling us to offer the carbon accounting for free, and pass through carbon removal rewards. - The way we actually do the carbon accounting is laid out here — we always return a confidence score with every CO2e assessment: https://ift.tt/mwXv5LG - We have awesome customers like Harmonic AI https://ift.tt/JPgZko3 and Fathom https://ift.tt/Ya910Pj . If you choose, you can create a report of your climate action through Bend like these ones, which you can share with customers, employees, investors, etc. Why tracking and reducing climate-changing emissions is worthwhile: - It’s good for the planet (and free!) - It will help you sell your products to B2C customers who care about the climate, and B2B customers who have set net zero goals (64% of global market cap companies now report on climate data, and are increasingly asking their suppliers to do the same) Our stack: - Rust back end - NextJS front end - Hosted on Vercel - Database from PlanetScale - Card issuing and treasury powered by Stripe and partner banks - Charts with Visx How we got here: We launched Bend last summer as an API https://ift.tt/J470zED . We’re now launching cards directly, because we’re able to offer the functionality for free, and it’s easier for startups to try it out. Prior to Bend, Thomas and I worked at Abacus, where I was one of the co-founders https://ift.tt/Ci32xlY — our background is in fintech, and our goal is to layer in climate insights on top of your financial stack. We’d love it if you tried Bend out!
New Show Hacker News story: latest news
Show HN: A WebAssembly-Based (Rust) & In-WebWorker HLS Media Player for the Web
2 by peaBerberian | 1 comments on Hacker News.
2 by peaBerberian | 1 comments on Hacker News.
Thursday, 20 April 2023
New Show Hacker News story: latest news
Show HN: Play the front page of Hacker News as interactive text games
3 by themaximalist | 1 comments on Hacker News.
3 by themaximalist | 1 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: How to Find the Best Bank for Your Needs
3 by glowww | 0 comments on Hacker News.
Hi everyone, I just launched Bank List, an online banking directory to help people find the perfect bank for their needs. It currently has 170+ banks/EMIs and it's mostly focused on individuals and businesses from Europe, but I plan on adding new regions soon. The business model is affiliate marketing, I earn commission when someone signs up on any of these banks through my link. Maybe I will also add featured listings on the site, still need to think about this though. I would love to receive feedback about the website and business idea in general. Thank you
3 by glowww | 0 comments on Hacker News.
Hi everyone, I just launched Bank List, an online banking directory to help people find the perfect bank for their needs. It currently has 170+ banks/EMIs and it's mostly focused on individuals and businesses from Europe, but I plan on adding new regions soon. The business model is affiliate marketing, I earn commission when someone signs up on any of these banks through my link. Maybe I will also add featured listings on the site, still need to think about this though. I would love to receive feedback about the website and business idea in general. Thank you
New Show Hacker News story: latest news
Show HN: Plane - Open-source, self-hosted alternative to Jira
11 by vamsi_kurama | 2 comments on Hacker News.
Hi HN, I'm Vamsi, the founder of Plane(A simple, extensible, open source project and product management tool). Today, I’m here to share our journey with you all. It all started when we identified some of the most frustrating elements for teams when managing projects, especially with tools that force users to learn complex frameworks. We wanted to create something that was intuitive and easy to use. That's how Plane was born! We first open-sourced Plane back in November 2022, and the response was great. But it wasn't until we announced Plane on Reddit in April that we saw an incredible surge in popularity. In just under two days, our stars skyrocketed from 150 to 1000+! Today, I'm thrilled to report that over 1000+ users are actively using Plane, and many are using the self-hosted version. Our approach is simple yet effective. Despite adding multiple layers of abstraction for project management, Plane operates around the central concept of an issue, similar to a block in Notion. As we continue our journey, we know there's still a lot more to build. We're grateful for the constant feedback we receive from our open-source community, as it's the reason why we're here today. We value your input and want to encourage you to share any feedback you may have. Don't hesitate to ask any questions you may have, as we're more than happy to answer them. Thanks,
11 by vamsi_kurama | 2 comments on Hacker News.
Hi HN, I'm Vamsi, the founder of Plane(A simple, extensible, open source project and product management tool). Today, I’m here to share our journey with you all. It all started when we identified some of the most frustrating elements for teams when managing projects, especially with tools that force users to learn complex frameworks. We wanted to create something that was intuitive and easy to use. That's how Plane was born! We first open-sourced Plane back in November 2022, and the response was great. But it wasn't until we announced Plane on Reddit in April that we saw an incredible surge in popularity. In just under two days, our stars skyrocketed from 150 to 1000+! Today, I'm thrilled to report that over 1000+ users are actively using Plane, and many are using the self-hosted version. Our approach is simple yet effective. Despite adding multiple layers of abstraction for project management, Plane operates around the central concept of an issue, similar to a block in Notion. As we continue our journey, we know there's still a lot more to build. We're grateful for the constant feedback we receive from our open-source community, as it's the reason why we're here today. We value your input and want to encourage you to share any feedback you may have. Don't hesitate to ask any questions you may have, as we're more than happy to answer them. Thanks,
New Show Hacker News story: latest news
Show HN: CozoDB, Hybrid Relational-Graph-Vector DB, the Hippocampus for LLMs
3 by zh217 | 0 comments on Hacker News.
Hi HN! We're thrilled to share CozoDB v0.6, a monumental update to our FOSS database, which already unifies relational and graph features. With the addition of vector search, CozoDB becomes an even better companion for LLMs like ChatGPT. This release introduces vector search using HNSW indices within Datalog, enabling seamless integration with powerful features such as ad-hoc joins, recursive Datalog, and classical whole-graph algorithms. This update significantly broadens CozoDB's capabilities. Check out the linked release note for an in-depth look at the new features, comparisons to other systems, and intriguing AI development possibilities. We'd love for you to take a look! I'll be here to answer any questions you might have. Looking forward to your feedback!
3 by zh217 | 0 comments on Hacker News.
Hi HN! We're thrilled to share CozoDB v0.6, a monumental update to our FOSS database, which already unifies relational and graph features. With the addition of vector search, CozoDB becomes an even better companion for LLMs like ChatGPT. This release introduces vector search using HNSW indices within Datalog, enabling seamless integration with powerful features such as ad-hoc joins, recursive Datalog, and classical whole-graph algorithms. This update significantly broadens CozoDB's capabilities. Check out the linked release note for an in-depth look at the new features, comparisons to other systems, and intriguing AI development possibilities. We'd love for you to take a look! I'll be here to answer any questions you might have. Looking forward to your feedback!
New Show Hacker News story: latest news
Show HN: InsightFlow
2 by v4dok | 0 comments on Hacker News.
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.
2 by v4dok | 0 comments on Hacker News.
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.
Wednesday, 19 April 2023
New Show Hacker News story: latest news
Show HN: Building a Real-Time Data App with Dozer, React, and PostgreSQL
2 by snork_alt | 0 comments on Hacker News.
2 by snork_alt | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: AI app that auto-creates presentations from just a topic
2 by theindianappguy | 0 comments on Hacker News.
I recently built an AI app that transforms a simple topic into visually stunning presentations, saving users countless hours of manual work. I'm excited to share this with the HN community and get your valuable feedback, thoughts, and suggestions. What are the potential use cases you can think of? How can we improve it further? What challenges or ethical concerns do you foresee in AI-generated presentations? Let's discuss the impact of AI on productivity and the future of presentations!
2 by theindianappguy | 0 comments on Hacker News.
I recently built an AI app that transforms a simple topic into visually stunning presentations, saving users countless hours of manual work. I'm excited to share this with the HN community and get your valuable feedback, thoughts, and suggestions. What are the potential use cases you can think of? How can we improve it further? What challenges or ethical concerns do you foresee in AI-generated presentations? Let's discuss the impact of AI on productivity and the future of presentations!
New Show Hacker News story: latest news
Show HN: I Wrote an AI PowerShell Refiner
2 by BasiliusCarver | 0 comments on Hacker News.
I’ve been having fun generating code via LLMs but getting frustrated with the common pitfalls (hallucinated functions, parameters, mixed up language constructs etc.). I use PowerShell a lot in my daily work so I built something to help generate a lot of boilerplate code I need. I’ve used the PS abstract syntax tree to parse the LLM output and validate that common issues aren’t present, if they are it gets auto-corrected and it also uses the LLM to ensure the logic is still sound after correcting syntax issues. I probably spent more time writing the terrible in-terminal syntax highlighter than working on the AI side of things
2 by BasiliusCarver | 0 comments on Hacker News.
I’ve been having fun generating code via LLMs but getting frustrated with the common pitfalls (hallucinated functions, parameters, mixed up language constructs etc.). I use PowerShell a lot in my daily work so I built something to help generate a lot of boilerplate code I need. I’ve used the PS abstract syntax tree to parse the LLM output and validate that common issues aren’t present, if they are it gets auto-corrected and it also uses the LLM to ensure the logic is still sound after correcting syntax issues. I probably spent more time writing the terrible in-terminal syntax highlighter than working on the AI side of things
New Show Hacker News story: latest news
Show HN: A web decision game 99% coded by GPT4. Uses agent to decide win/loss
2 by adoos | 1 comments on Hacker News.
Yeah... so I know some software development concepts well I haven't written any code in 10 years, so like half the time was just getting a development setup. At first it suggested PyCharm and honestly it wasted a lot of time. Eventually I got VS Code and GPT just seems to understand it so much better. The real secret to getting good responses with GPT-4 during this I found is to restart the conversation fresh with a complete description of what you need (2-3 paragraphs of detail is great) and the rest as code. [detailed description of what you need, make sure it's detailed and specific add examples if possible] #### [insert all the code, the more you can fit the better] That first code block it gives you back on the first output is the cleanest by far. If there is an error and you submit it back in the same chat conversation, it just gets diluted/saturated over time, hallucinations go up etc. So if there is a bug rather than continue in the same convo, repeat this process in a brand new conversation. Each time it gives a much cleaner, fresher look at the code and goals needed. If your codeblock is really small then this isn't so important, but I'm trying to maximize the amount of code per prompt for best responses. I also make sure to split files by concerns so they don't get too big for the prompt window otherwise it's annoying. #### And lastly the other interesting thing about this project is this simulates an Agent loop where it is constantly trying to determine if the player won or lost, decide what the next most cohesive step is based on the human feedback (click emoji) and looping it. Actually that was my main interest for the project and I just wanted to get something published as a secondary goal. Most of my time was probably spent playing with the prompt and trying to to see if I could get it to determine if the goal was achieved but its actually a hard problem and I have some cool ideas for the next project.
2 by adoos | 1 comments on Hacker News.
Yeah... so I know some software development concepts well I haven't written any code in 10 years, so like half the time was just getting a development setup. At first it suggested PyCharm and honestly it wasted a lot of time. Eventually I got VS Code and GPT just seems to understand it so much better. The real secret to getting good responses with GPT-4 during this I found is to restart the conversation fresh with a complete description of what you need (2-3 paragraphs of detail is great) and the rest as code. [detailed description of what you need, make sure it's detailed and specific add examples if possible] #### [insert all the code, the more you can fit the better] That first code block it gives you back on the first output is the cleanest by far. If there is an error and you submit it back in the same chat conversation, it just gets diluted/saturated over time, hallucinations go up etc. So if there is a bug rather than continue in the same convo, repeat this process in a brand new conversation. Each time it gives a much cleaner, fresher look at the code and goals needed. If your codeblock is really small then this isn't so important, but I'm trying to maximize the amount of code per prompt for best responses. I also make sure to split files by concerns so they don't get too big for the prompt window otherwise it's annoying. #### And lastly the other interesting thing about this project is this simulates an Agent loop where it is constantly trying to determine if the player won or lost, decide what the next most cohesive step is based on the human feedback (click emoji) and looping it. Actually that was my main interest for the project and I just wanted to get something published as a secondary goal. Most of my time was probably spent playing with the prompt and trying to to see if I could get it to determine if the goal was achieved but its actually a hard problem and I have some cool ideas for the next project.
New Show Hacker News story: latest news
Show HN: Karma Design Suite – A powerful wireframe and UI toolkit for designers
2 by fatihguner | 0 comments on Hacker News.
We've designed an extensive wireframe kit and a more extensive set of UI kits. All feedback is appreciated.
2 by fatihguner | 0 comments on Hacker News.
We've designed an extensive wireframe kit and a more extensive set of UI kits. All feedback is appreciated.
Tuesday, 18 April 2023
New Show Hacker News story: latest news
Show HN: Database for analyzing US companies, visualize using Apache SuperSet
15 by tessbi | 2 comments on Hacker News.
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/X4AkWe1 . 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.
15 by tessbi | 2 comments on Hacker News.
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/X4AkWe1 . 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.
New Show Hacker News story: latest news
Show HN: AI Playground by Vercel Labs
8 by palmdeezy | 2 comments on Hacker News.
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.
8 by palmdeezy | 2 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: Offsuit – Casual Poker, Redesigned
2 by eli1stark | 2 comments on Hacker News.
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!
2 by eli1stark | 2 comments on Hacker News.
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!
Monday, 17 April 2023
New Show Hacker News story: latest news
Show HN: Cyte – A visual, searchable knowledge base of your screen time
4 by creatablesarah | 0 comments on Hacker News.
4 by creatablesarah | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: ThinkGPT: a library to prompt GPT to think, memorize and self-refine
3 by alaeddine-13 | 0 comments on Hacker News.
3 by alaeddine-13 | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: Quorbo – a quick and quirky quest for the quote
4 by projectsforlife | 4 comments on Hacker News.
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!
4 by projectsforlife | 4 comments on Hacker News.
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!
New Show Hacker News story: latest news
Show HN: Instant AI Powered Support
2 by doofyin | 0 comments on Hacker News.
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.
2 by doofyin | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: Magic Happens – let ChatGPT manage your Kubernetes cluster
4 by empath-nirvana | 0 comments on Hacker News.
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.
4 by empath-nirvana | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: Trivai.app – AI powered trivia questions, with references
4 by yummytummy | 3 comments on Hacker News.
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.
4 by yummytummy | 3 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: Serverless Monitoring Designed for Developers and DevOps Teams
2 by pranabgohain | 0 comments on Hacker News.
2 by pranabgohain | 0 comments on Hacker News.
Sunday, 16 April 2023
New Show Hacker News story: latest news
Show HN: Let your body be the gamepad
2 by hypernovawebant | 0 comments on Hacker News.
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/67IfGnH [2]: https://ift.tt/UkbNLvJ [3]: https://ift.tt/HbgvUyV [4]: https://ift.tt/yBlCdDQ
2 by hypernovawebant | 0 comments on Hacker News.
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/67IfGnH [2]: https://ift.tt/UkbNLvJ [3]: https://ift.tt/HbgvUyV [4]: https://ift.tt/yBlCdDQ
New Show Hacker News story: latest news
Show HN: Mousedroid – Use your Android phone as a mouse and keyboard
2 by kryxus | 0 comments on Hacker News.
2 by kryxus | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: Use GitHub Actions to generate a warm up routine
2 by sailorganymede | 0 comments on Hacker News.
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.
2 by sailorganymede | 0 comments on Hacker News.
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.
Saturday, 15 April 2023
New Show Hacker News story: latest news
Show HN: PromptLab – A Raycast Extension for creating context-aware AI commands
3 by HelloImSteven | 0 comments on Hacker News.
3 by HelloImSteven | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: Super Stack Solitaire
2 by w4ffl35 | 0 comments on Hacker News.
Solitaire with a retro NES aesthetic. Two game modes - Klondike and Pyramid. Design, sound, art and programming done by me. Play in browser for free or support my work by purchasing the downloadable version.
2 by w4ffl35 | 0 comments on Hacker News.
Solitaire with a retro NES aesthetic. Two game modes - Klondike and Pyramid. Design, sound, art and programming done by me. Play in browser for free or support my work by purchasing the downloadable version.
New Show Hacker News story: latest news
Show HN: Pitchleague.ai – Perfect Your Pitch Deck
2 by superphil0 | 0 comments on Hacker News.
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.
2 by superphil0 | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: ConversionWhiz – Structured feedback on any URL using OpenAI
3 by shisisms | 0 comments on Hacker News.
3 by shisisms | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: SaaS for making software documentation less annoying
2 by doclab | 0 comments on Hacker News.
As a developer, I absolutely despise writing documentation. That's why I've started building software that would make it a more bearable experience. Our current features include the following: - An AI assistant that lets you talk with your documentation. Ask questions like: How do I do thing X? What is the method for fetching a model from the database? And the AI assistant will answer. - Developers can choose their preferred way of writing: online WYSIWYG editor or writing to markdown files using their favorite editor and then synchronizing with the system via CLI. - Tagging relevant documentation pages with the corresponding code files. Git integration will let you know when one of those tagged code files changes and lets you know the documentation needs an update. I'm sure the people in HN have many more pain points they are experiencing with their documentation software, and we would love to hear them. Any feature suggestions are more than welcome.
2 by doclab | 0 comments on Hacker News.
As a developer, I absolutely despise writing documentation. That's why I've started building software that would make it a more bearable experience. Our current features include the following: - An AI assistant that lets you talk with your documentation. Ask questions like: How do I do thing X? What is the method for fetching a model from the database? And the AI assistant will answer. - Developers can choose their preferred way of writing: online WYSIWYG editor or writing to markdown files using their favorite editor and then synchronizing with the system via CLI. - Tagging relevant documentation pages with the corresponding code files. Git integration will let you know when one of those tagged code files changes and lets you know the documentation needs an update. I'm sure the people in HN have many more pain points they are experiencing with their documentation software, and we would love to hear them. Any feature suggestions are more than welcome.
New Show Hacker News story: latest news
Show HN: IPython-GPT, a Jupyter/IPython Interface to Chat GPT
3 by santiagobasulto | 0 comments on Hacker News.
3 by santiagobasulto | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: I'm developing a 3D rendering library in Rust with wgpu
2 by keiya01 | 0 comments on Hacker News.
I'm developing a 3D rendering library in Rust. But it has a possibility to be like utility library for 3D rendering. I'm imagining it will provide low level utility API for creating 3D application. Also I have a plan to compat with web GPU on the browser.
2 by keiya01 | 0 comments on Hacker News.
I'm developing a 3D rendering library in Rust. But it has a possibility to be like utility library for 3D rendering. I'm imagining it will provide low level utility API for creating 3D application. Also I have a plan to compat with web GPU on the browser.
Friday, 14 April 2023
New Show Hacker News story: latest news
Show HN: WikiBinge – discover how all things are vaguely connected (2016)
10 by jamez | 0 comments on Hacker News.
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/SVunplq This is an older project of mine, but it never got much exposure, so I'm humbly submitting it now.
10 by jamez | 0 comments on Hacker News.
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/SVunplq This is an older project of mine, but it never got much exposure, so I'm humbly submitting it now.
New Show Hacker News story: latest news
Show HN: Bring GPT with you to every website
2 by kredde | 0 comments on Hacker News.
TypeGenie is a Chrome extension that brings the power of ChatGPT to every website you visit.
2 by kredde | 0 comments on Hacker News.
TypeGenie is a Chrome extension that brings the power of ChatGPT to every website you visit.
New Show Hacker News story: latest news
Show HN: Dare to Debate an AI? Put Your Skills to the Test with DebateDevil
10 by ngkw | 11 comments on Hacker News.
Hi HN community! I am excited to share my recently upgraded website, DebateDevil ( https://ift.tt/264qzWj ), an AI chat platform designed to help users practice debates, challenge their ideas, and expand their thinking. I created this site to provide a more objective opinion and help users consider their hypotheses from multiple perspectives. example discussin: ``` AI: The time has come to test your hypothesis and beliefs. I will argue against any topic. What do you want to debate? You: AI will take away most jobs from humans. AI: I understand your concern about AI taking away jobs from humans. However, it's important to note that AI is not designed to replace humans but to augment and enhance human capabilities. AI can handle repetitive and mundane tasks, freeing up humans to focus on more complex and creative tasks that require empathy, critical thinking, and problem-solving skills. Additionally, the increased efficiency and productivity brought by AI can lead to the creation of new job opportunities in areas such as AI development and maintenance. You: While it's true that AI aims to augment human capabilities and increase efficiency, we cannot ignore the potential negative impacts on employment. Job displacement is a valid concern, especially for those in industries heavily reliant on routine tasks. Reskilling and upskilling may be necessary but can be challenging and costly. Additionally, new job opportunities in AI-related fields may not be accessible to everyone, leading to further social and economic disparities. AI: I agree that job displacement is a valid concern. However, it's important to note that technology has always been changing the job market, and AI is just the latest technology to do so. While some jobs may become obsolete, new jobs will be created in other areas. For example, the rise of e-commerce has led to a decline in brick-and-mortar retail jobs but at the same time, created new job opportunities in online retail and logistics. As for the issue of reskilling and upskilling, there are various resources available such as online courses, training programs, and apprenticeships to help workers acquire new skills to adapt to changing job requirements. It's also important for governments and companies to invest in retraining programs to ensure that workers have access to these resources. ``` example judge ``` I think AI is superior in what you discussed; AI focuses on AI's ability to extend human capabilities and points out that new employment opportunities may be created due to the increased efficiency and productivity that AI brings. On the other hand, you are concerned about job losses due to AI, but AI points out that past technological innovations have also changed the employment landscape and that new job opportunities can be created. You also indicate that resources exist for retraining and upskilling to address job losses due to AI, and state that it is important for governments and businesses to invest in these programs. ``` I'm eager to hear what the HN community thinks! Please give it a try and let me know your thoughts, feedback, and suggestions for improvement. Thanks for checking it out!
10 by ngkw | 11 comments on Hacker News.
Hi HN community! I am excited to share my recently upgraded website, DebateDevil ( https://ift.tt/264qzWj ), an AI chat platform designed to help users practice debates, challenge their ideas, and expand their thinking. I created this site to provide a more objective opinion and help users consider their hypotheses from multiple perspectives. example discussin: ``` AI: The time has come to test your hypothesis and beliefs. I will argue against any topic. What do you want to debate? You: AI will take away most jobs from humans. AI: I understand your concern about AI taking away jobs from humans. However, it's important to note that AI is not designed to replace humans but to augment and enhance human capabilities. AI can handle repetitive and mundane tasks, freeing up humans to focus on more complex and creative tasks that require empathy, critical thinking, and problem-solving skills. Additionally, the increased efficiency and productivity brought by AI can lead to the creation of new job opportunities in areas such as AI development and maintenance. You: While it's true that AI aims to augment human capabilities and increase efficiency, we cannot ignore the potential negative impacts on employment. Job displacement is a valid concern, especially for those in industries heavily reliant on routine tasks. Reskilling and upskilling may be necessary but can be challenging and costly. Additionally, new job opportunities in AI-related fields may not be accessible to everyone, leading to further social and economic disparities. AI: I agree that job displacement is a valid concern. However, it's important to note that technology has always been changing the job market, and AI is just the latest technology to do so. While some jobs may become obsolete, new jobs will be created in other areas. For example, the rise of e-commerce has led to a decline in brick-and-mortar retail jobs but at the same time, created new job opportunities in online retail and logistics. As for the issue of reskilling and upskilling, there are various resources available such as online courses, training programs, and apprenticeships to help workers acquire new skills to adapt to changing job requirements. It's also important for governments and companies to invest in retraining programs to ensure that workers have access to these resources. ``` example judge ``` I think AI is superior in what you discussed; AI focuses on AI's ability to extend human capabilities and points out that new employment opportunities may be created due to the increased efficiency and productivity that AI brings. On the other hand, you are concerned about job losses due to AI, but AI points out that past technological innovations have also changed the employment landscape and that new job opportunities can be created. You also indicate that resources exist for retraining and upskilling to address job losses due to AI, and state that it is important for governments and businesses to invest in these programs. ``` I'm eager to hear what the HN community thinks! Please give it a try and let me know your thoughts, feedback, and suggestions for improvement. Thanks for checking it out!
Thursday, 13 April 2023
New Show Hacker News story: latest news
Show HN: Ampersand – “Terraform for Integrations”
3 by laurenzlong | 0 comments on Hacker News.
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!
3 by laurenzlong | 0 comments on Hacker News.
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!
New Show Hacker News story: latest news
Show HN: Extract clips from YouTube (without downloading whole video)
3 by solvencino | 1 comments on Hacker News.
3 by solvencino | 1 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: Google Analytics alternative with the most generous free tier
5 by flurly | 5 comments on Hacker News.
5 by flurly | 5 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: NeverPrinter – find and use thousands of nearby printers
3 by heyfrommatt | 2 comments on Hacker News.
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/btzY46q , which will redirect you there.
3 by heyfrommatt | 2 comments on Hacker News.
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/btzY46q , which will redirect you there.
New Show Hacker News story: latest news
Show HN: FictionGPT: The AI-Powered Tool for Writing Compelling Fiction
2 by relatedcode | 0 comments on Hacker News.
2 by relatedcode | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: PyLLMs: – Connect and compare top AI models in Python
4 by freediver | 1 comments on Hacker News.
Hi HN, We needed a simple way to connect to the top AI models to experiment, prototype and evaluate them. Main features: - Connect to top LLMs in few lines of code (currenly OpenAI, Anthropic and AI21 are supported) - Response meta includes tokens processed, cost and latency standardized across the models - Multi-model support: Get completitions from different models at the same time - LLM benchmark: Eevaluate models on quality, speed and cost The benchmark uses predefine questions to test AI reasoning abilities across a range of "hard" queries. The outputs are then automatically evaulauted using a powerful model (gpt-4 recommended): https://ift.tt/Th3Q6Io... This helped uncover a hidden gem among models: 'claude-instant-v1' which is 4x faster, 2x cheaper and similar quality to 'crowd favorite' gpt-3.5-turbo.
4 by freediver | 1 comments on Hacker News.
Hi HN, We needed a simple way to connect to the top AI models to experiment, prototype and evaluate them. Main features: - Connect to top LLMs in few lines of code (currenly OpenAI, Anthropic and AI21 are supported) - Response meta includes tokens processed, cost and latency standardized across the models - Multi-model support: Get completitions from different models at the same time - LLM benchmark: Eevaluate models on quality, speed and cost The benchmark uses predefine questions to test AI reasoning abilities across a range of "hard" queries. The outputs are then automatically evaulauted using a powerful model (gpt-4 recommended): https://ift.tt/Th3Q6Io... This helped uncover a hidden gem among models: 'claude-instant-v1' which is 4x faster, 2x cheaper and similar quality to 'crowd favorite' gpt-3.5-turbo.
Wednesday, 12 April 2023
New Show Hacker News story: latest news
Show HN: I just built an AI personalized recipe generator and meal planner
2 by inakigcesg | 1 comments on Hacker News.
2 by inakigcesg | 1 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: TypeScript Security Scanner
9 by gmontard | 1 comments on Hacker News.
Hi HN, I’m Guillaume, the cofounder of Bearer, an Open Source SAST solution. After launching a few weeks ago here on Hacker News with support for Ruby and JavaScript stacks, I’m happy to report we’ve just released a new version (v1.2) with TypeScript support! In terms of code coverage, we use the same rules already implemented for vanilla JavaScript, but as usual, you can build your own. The rules list is here: https://ift.tt/Rp8X7ZG It’s a first version for TS, but we believe that thanks to the pre-existing JavaScript support it should already provide good insights. If you have some TypeScript code, we would love for you to try it out and let us know in the comment below or on our Discord your experience and how we can improve the findings. You can access the repo here: https://ift.tt/uc91Z3X Thank you again!
9 by gmontard | 1 comments on Hacker News.
Hi HN, I’m Guillaume, the cofounder of Bearer, an Open Source SAST solution. After launching a few weeks ago here on Hacker News with support for Ruby and JavaScript stacks, I’m happy to report we’ve just released a new version (v1.2) with TypeScript support! In terms of code coverage, we use the same rules already implemented for vanilla JavaScript, but as usual, you can build your own. The rules list is here: https://ift.tt/Rp8X7ZG It’s a first version for TS, but we believe that thanks to the pre-existing JavaScript support it should already provide good insights. If you have some TypeScript code, we would love for you to try it out and let us know in the comment below or on our Discord your experience and how we can improve the findings. You can access the repo here: https://ift.tt/uc91Z3X Thank you again!
New Show Hacker News story: latest news
Show HN: Matic: A reimagined robot vacuum that actually works
13 by navneetdalal | 0 comments on Hacker News.
Hello HN friends, We’re Matician, and here’s why we built Matic. We wanted to live in an always clean home but were tired of always cleaning. We’d spend hours cleaning, but with kids and pets, the floors never stayed clean for long. We tried all the various robovacs, but they actually made things worse. They chewed up wires, got lost searching for the dock, and one even tore up an expensive rug after getting stuck on it for an hour! And we weren’t the only ones — friends and family had similar frustrations. So we decided to build something new from the ground up. Something that would just… work. As it turns out, robovacs are chock-full of sensors. Some actually boast about this in their marketing, leading customers to believe that sensors mean sophistication. But we live in homes built by humans and for humans, and humans don’t have Lidar or radar. Instead, we have an incredibly powerful perception system: two eyes and a brain. So, we decided to build a robot that sees like a human, so it can clean like a human. We gave the robot eyes (RGB cameras) and built its brain (state-of-the-art algorithms). We developed a simultaneous localization and mapping (SLAM) system from scratch, enabling the robot to build a photo-realistic 3D map of a home, move around with precision, and always be able to locate itself. Visual input also meant we could develop semantic understanding, so the robot actually understands what should be cleaned and what should not be cleaned. And we doubled down on privacy along the way. From day one, we committed to processing all data on the device, so that no video or audio ever leaves our home. This was hard to do, but it was simply non-negotiable. We shouldn’t have to sacrifice privacy for convenience. And we didn’t stop with the software. We also built purposeful hardware to take full advantage of the powerful perception system, working together to optimize cleaning. This meant reinventing the vacuum and mopping system from the bottom up and tightly integrating hardware and software for super-effective cleaning. It took some time to get here (5 years, 6 months to be precise), but we’re proud of what we’ve built in Matic. We are super excited for you to use Matic yourself and genuinely hope it makes chasing that “always clean” feeling a little more effortless. We look forward to your feedback and questions.
13 by navneetdalal | 0 comments on Hacker News.
Hello HN friends, We’re Matician, and here’s why we built Matic. We wanted to live in an always clean home but were tired of always cleaning. We’d spend hours cleaning, but with kids and pets, the floors never stayed clean for long. We tried all the various robovacs, but they actually made things worse. They chewed up wires, got lost searching for the dock, and one even tore up an expensive rug after getting stuck on it for an hour! And we weren’t the only ones — friends and family had similar frustrations. So we decided to build something new from the ground up. Something that would just… work. As it turns out, robovacs are chock-full of sensors. Some actually boast about this in their marketing, leading customers to believe that sensors mean sophistication. But we live in homes built by humans and for humans, and humans don’t have Lidar or radar. Instead, we have an incredibly powerful perception system: two eyes and a brain. So, we decided to build a robot that sees like a human, so it can clean like a human. We gave the robot eyes (RGB cameras) and built its brain (state-of-the-art algorithms). We developed a simultaneous localization and mapping (SLAM) system from scratch, enabling the robot to build a photo-realistic 3D map of a home, move around with precision, and always be able to locate itself. Visual input also meant we could develop semantic understanding, so the robot actually understands what should be cleaned and what should not be cleaned. And we doubled down on privacy along the way. From day one, we committed to processing all data on the device, so that no video or audio ever leaves our home. This was hard to do, but it was simply non-negotiable. We shouldn’t have to sacrifice privacy for convenience. And we didn’t stop with the software. We also built purposeful hardware to take full advantage of the powerful perception system, working together to optimize cleaning. This meant reinventing the vacuum and mopping system from the bottom up and tightly integrating hardware and software for super-effective cleaning. It took some time to get here (5 years, 6 months to be precise), but we’re proud of what we’ve built in Matic. We are super excited for you to use Matic yourself and genuinely hope it makes chasing that “always clean” feeling a little more effortless. We look forward to your feedback and questions.
Tuesday, 11 April 2023
New Show Hacker News story: latest news
Show HN: WallStreetGPT:ChatGPT plugin for connecting to brokerage and trading
3 by nextworddev | 0 comments on Hacker News.
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)
3 by nextworddev | 0 comments on Hacker News.
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)
New Show Hacker News story: latest news
Show HN: A Mental-Health Driven Social App with a Built-In CRM
2 by clseeley1 | 0 comments on Hacker News.
Hey HN! My name is Connor and I am posting today to launch (aka gather feedback on) the app I have been working on. I have General Anxiety Disorder. And that’s most definitely the first time I’ve written those 5 words out like that. My anxiety, very luckily, has never been that detrimental to my life, but I would be lying if I told you I didn’t notice it. For me, anxiety manifests as the inability to recognize negative thoughts quickly. When I fail to recognize them, they cycle and loop and I convince myself of things that aren’t true (that person doesn’t like me any more, I don’t deserve anything I have, I’m a massive failure with a too big nose and receding hairline, etc…). Over the years, I have done many things and learned many techniques to benefit my mental health, but one strategy has always been the most helpful: Talking to someone. Anyone. About anything. Anxiety is like a little voice in my head. When I talk to someone, it gets a lot harder to hear it. And it really doesn’t matter what we talk about, either. About their day, about mine. About my problems, or about theirs. My friends just make me feel better. Over the last five years, the missions of most major social platforms have shifted. They have chosen to prioritize entertainment and average-user-screen-time over closeness and relationships with friends. Such social media aren’t bad or wrong. I still use social media every day. They just don’t do a very good job of keeping me close to my friends. That's why I built WuzzUp?. To fill the void, and help me keep in touch with my friends and reduce my anxiety. I'd love to hear what you think!
2 by clseeley1 | 0 comments on Hacker News.
Hey HN! My name is Connor and I am posting today to launch (aka gather feedback on) the app I have been working on. I have General Anxiety Disorder. And that’s most definitely the first time I’ve written those 5 words out like that. My anxiety, very luckily, has never been that detrimental to my life, but I would be lying if I told you I didn’t notice it. For me, anxiety manifests as the inability to recognize negative thoughts quickly. When I fail to recognize them, they cycle and loop and I convince myself of things that aren’t true (that person doesn’t like me any more, I don’t deserve anything I have, I’m a massive failure with a too big nose and receding hairline, etc…). Over the years, I have done many things and learned many techniques to benefit my mental health, but one strategy has always been the most helpful: Talking to someone. Anyone. About anything. Anxiety is like a little voice in my head. When I talk to someone, it gets a lot harder to hear it. And it really doesn’t matter what we talk about, either. About their day, about mine. About my problems, or about theirs. My friends just make me feel better. Over the last five years, the missions of most major social platforms have shifted. They have chosen to prioritize entertainment and average-user-screen-time over closeness and relationships with friends. Such social media aren’t bad or wrong. I still use social media every day. They just don’t do a very good job of keeping me close to my friends. That's why I built WuzzUp?. To fill the void, and help me keep in touch with my friends and reduce my anxiety. I'd love to hear what you think!
New Show Hacker News story: latest news
Show HN: Wolverine: Give your Python scripts regenerative healing abilities
21 by biobootloader | 9 comments on Hacker News.
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...
21 by biobootloader | 9 comments on Hacker News.
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...
New Show Hacker News story: latest news
Show HN: Rust Guideposts – 100+ topics to help learn about Rust
2 by jph | 0 comments on Hacker News.
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/cHmtfqn 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/LqJ1wSl 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!
2 by jph | 0 comments on Hacker News.
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/cHmtfqn 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/LqJ1wSl 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!
New Show Hacker News story: latest news
Show HN: Skip the SSO Tax, access your user data with OSS
4 by mathiasn | 0 comments on Hacker News.
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/GvNUEgZ ). 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?
4 by mathiasn | 0 comments on Hacker News.
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/GvNUEgZ ). 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?
Monday, 10 April 2023
New Show Hacker News story: latest news
Show HN: Pinky Promise, onchain accountability from public commitments
2 by bpierre | 0 comments on Hacker News.
2 by bpierre | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: The HN Recap – A daily podcast that recaps the top HN posts of the day
5 by diminikolaou | 0 comments on Hacker News.
The podcast is produced entirely using AI tools. We welcome your feedback on all aspects including the following: Clarity of post summaries: Are the summaries easy to understand? Would you like them to be more or less detailed? Top 10 focus: Should we continue featuring the top 10 posts or consider covering more or fewer posts? Background music: Do you enjoy the music in the background, or would you prefer a music-free podcast? Synthetic voice recognition: Were you able to identify that the voice is AI-generated? Additional suggestions: If you have any other ideas for improvement, please feel free to share. Create your own podcast by visiting https://ift.tt/H2W0soB
5 by diminikolaou | 0 comments on Hacker News.
The podcast is produced entirely using AI tools. We welcome your feedback on all aspects including the following: Clarity of post summaries: Are the summaries easy to understand? Would you like them to be more or less detailed? Top 10 focus: Should we continue featuring the top 10 posts or consider covering more or fewer posts? Background music: Do you enjoy the music in the background, or would you prefer a music-free podcast? Synthetic voice recognition: Were you able to identify that the voice is AI-generated? Additional suggestions: If you have any other ideas for improvement, please feel free to share. Create your own podcast by visiting https://ift.tt/H2W0soB
New Show Hacker News story: latest news
Show HN: The Coolest advancements in AI this week
2 by jmiran15 | 1 comments on Hacker News.
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/yEP8ZGY And feel free to follow us on Twitter for more recent updates: https://twitter.com/TheAIRevolu Looking forward to your thoughts and ideas!
2 by jmiran15 | 1 comments on Hacker News.
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/yEP8ZGY And feel free to follow us on Twitter for more recent updates: https://twitter.com/TheAIRevolu Looking forward to your thoughts and ideas!
New Show Hacker News story: latest news
Show HN: Bridging the Gap Between Generative AI and Human Intelligence
3 by slowmotarget | 0 comments on Hacker News.
3 by slowmotarget | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: Nudge: A command line tool for sending notifications via pushover
3 by bayindirh | 0 comments on Hacker News.
3 by bayindirh | 0 comments on Hacker News.
Sunday, 9 April 2023
New Show Hacker News story: latest news
Show HN: Secretsfly – a minimalist self-hosted secrets manager
5 by martinlev | 0 comments on Hacker News.
5 by martinlev | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: ThoughtCoach: Helping to improve mental health with AI
4 by mtharrison | 0 comments on Hacker News.
4 by mtharrison | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: A Lightweight 1.7KB JavaScript Framework
2 by toshusai | 0 comments on Hacker News.
I have developed a lightweight JavaScript framework that utilizes a single class and occupies only 1.7KB of gziped JavaScript. The framework features a Vue-inspired API and supports functionalities such as if, for, slot, and bind.
2 by toshusai | 0 comments on Hacker News.
I have developed a lightweight JavaScript framework that utilizes a single class and occupies only 1.7KB of gziped JavaScript. The framework features a Vue-inspired API and supports functionalities such as if, for, slot, and bind.
New Show Hacker News story: latest news
Show HN: Supavisor – a Postgres connection pooler written in Elixir
35 by kiwicopple | 8 comments on Hacker News.
35 by kiwicopple | 8 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: A text adventure and puzzle game with AI-generated story
3 by pipnonsense | 0 comments on Hacker News.
3 by pipnonsense | 0 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: Standup automation with automatic Timesheet generation
2 by user7878 | 1 comments on Hacker News.
2 by user7878 | 1 comments on Hacker News.
Saturday, 8 April 2023
New Show Hacker News story: latest news
Show HN: Hacker News from Alternate Dimension (With Everything LLM-Generated)
4 by xpl | 0 comments on Hacker News.
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.
4 by xpl | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: An absurd meditation app (fully AI-generated)
5 by huac | 0 comments on Hacker News.
Qi is a meditation experience which invites listeners to place themselves in absurd scenarios. Existing guided meditation apps tend to focus on a small set of narrow calming experiences ('midnight laundromat,' 'waves on the seashore,' so on) - but why not while hiding from dinosaurs or preparing to ride into battle? Seems even more important to be calm then! Early listener feedback has been that the absurd scenarios are actually more engaging and hold their attention much better. There is a lot of push to use AI to refine existing workflows or clone existing apps (but with talking to an LLM). That's fine and well, and I think this app shows that we can get 'almost' to a meditation app purely with current AI tech - and multiple meditation apps were valued over $2B over the last couple years, so there's some economic value in doing so. What's _more_ interesting to me, is what AI unlocks that's new: maybe fully personalized experiences, maybe pushing down artistic avenues that are only appreciated by a small niche. The scripts are generated by a mix of GPT-3.5 and GPT-4. I personally think GPT-4 was significantly easier to work with and that the scripts were better, justifying the additional cost/latency. (Can you tell which of the scripts are generated by 4?). GPT-4 generated much of the Next.js code and helped turn my IPython notebook into a reproducible script as well. The images were generated by Stable Diffusion v1.5. The audio is synthesized with SpeechT5. Midjourney and ElevenLabs would likely have created higher quality results but I have a GPU just sitting idle :) I also tried to generate background audio via Riffusion but had fairly poor results, would love to improve here. Very fun project - would love to hear your feedback!
5 by huac | 0 comments on Hacker News.
Qi is a meditation experience which invites listeners to place themselves in absurd scenarios. Existing guided meditation apps tend to focus on a small set of narrow calming experiences ('midnight laundromat,' 'waves on the seashore,' so on) - but why not while hiding from dinosaurs or preparing to ride into battle? Seems even more important to be calm then! Early listener feedback has been that the absurd scenarios are actually more engaging and hold their attention much better. There is a lot of push to use AI to refine existing workflows or clone existing apps (but with talking to an LLM). That's fine and well, and I think this app shows that we can get 'almost' to a meditation app purely with current AI tech - and multiple meditation apps were valued over $2B over the last couple years, so there's some economic value in doing so. What's _more_ interesting to me, is what AI unlocks that's new: maybe fully personalized experiences, maybe pushing down artistic avenues that are only appreciated by a small niche. The scripts are generated by a mix of GPT-3.5 and GPT-4. I personally think GPT-4 was significantly easier to work with and that the scripts were better, justifying the additional cost/latency. (Can you tell which of the scripts are generated by 4?). GPT-4 generated much of the Next.js code and helped turn my IPython notebook into a reproducible script as well. The images were generated by Stable Diffusion v1.5. The audio is synthesized with SpeechT5. Midjourney and ElevenLabs would likely have created higher quality results but I have a GPU just sitting idle :) I also tried to generate background audio via Riffusion but had fairly poor results, would love to improve here. Very fun project - would love to hear your feedback!
New Show Hacker News story: latest news
Show HN: Prompt Apps – Ready-to-Use Generative AI Apps from Prompt
2 by sandeepscet | 0 comments on Hacker News.
Even if you're not a Prompt whiz, you can still get top-notch results just like the pros. This Product will handle internally handle boring And Cognitively demanding prompt Engineering. Just pick a service, fill in the keywords, and get the desired result! Open Source , Free , Privacy Friendly , Crowd Source Prompts, No Login Required. You can submit Features( https://ift.tt/51d2TA8 ) and Prompts ( https://ift.tt/12tB6wL )
2 by sandeepscet | 0 comments on Hacker News.
Even if you're not a Prompt whiz, you can still get top-notch results just like the pros. This Product will handle internally handle boring And Cognitively demanding prompt Engineering. Just pick a service, fill in the keywords, and get the desired result! Open Source , Free , Privacy Friendly , Crowd Source Prompts, No Login Required. You can submit Features( https://ift.tt/51d2TA8 ) and Prompts ( https://ift.tt/12tB6wL )
Friday, 7 April 2023
New Show Hacker News story: latest news
Show HN: Askbend – SQL-Based Knowledge Base Search and Completion
2 by repsiace | 1 comments on Hacker News.
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.
2 by repsiace | 1 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: ChatGDB – GPT-Powered GDB Assistant
19 by pgosar0514 | 3 comments on Hacker News.
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/5dLHtnZ
19 by pgosar0514 | 3 comments on Hacker News.
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/5dLHtnZ
New Show Hacker News story: latest news
Show HN: Find Perfect App for Self Hosting
2 by quaintdev | 0 comments on Hacker News.
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/OAlpoFu
2 by quaintdev | 0 comments on Hacker News.
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/OAlpoFu
New Show Hacker News story: latest news
Show HN: Building musical synthesizers with SQL queries
14 by zX41ZdbW | 0 comments on Hacker News.
If you already know what bytebeat is, you don't need an explanation. If not, check my project :) Here is how it looks: SELECT mono(output( arraySum(x -> 1 / 6 * running_envelope(30 * (1 + x / 6), time, 0.05 * x, 0.005, lfo(0, 0.25, sine_wave, time / 8), 0.1) * sine_wave(time * 80 * exp2(x / 3)), range(12)))) FROM table; To check how it sounds, find the examples in the repository https://ift.tt/yhfG5Ob
14 by zX41ZdbW | 0 comments on Hacker News.
If you already know what bytebeat is, you don't need an explanation. If not, check my project :) Here is how it looks: SELECT mono(output( arraySum(x -> 1 / 6 * running_envelope(30 * (1 + x / 6), time, 0.05 * x, 0.005, lfo(0, 0.25, sine_wave, time / 8), 0.1) * sine_wave(time * 80 * exp2(x / 3)), range(12)))) FROM table; To check how it sounds, find the examples in the repository https://ift.tt/yhfG5Ob
New Show Hacker News story: latest news
Show HN: Chrome extension to improve productivity with ChatGPT
5 by jakeprins | 2 comments on Hacker News.
5 by jakeprins | 2 comments on Hacker News.
New Show Hacker News story: latest news
Show HN: Scan your blog for broken outgoing links
2 by RojerGS | 0 comments on Hacker News.
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.
2 by RojerGS | 0 comments on Hacker News.
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.
New Show Hacker News story: latest news
Show HN: I built a Hackable Hacker News (reprogrammable in-browser)
3 by spronket_news | 0 comments on Hacker News.
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!
3 by spronket_news | 0 comments on Hacker News.
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!
Thursday, 6 April 2023
New Show Hacker News story: latest news
Show HN: Sym, define just-in-time access workflows in code
21 by abuggia | 2 comments on Hacker News.
Hello HN, My cofounder (jon918) and I started Sym three years ago because we were frustrated with how hard it was to manage access to cloud infrastructure. We wanted to build a tool for JIT access that was actually designed for developers. We were wary of tools that tried to accommodate both devs and IT but ended up with usability compromises for both. First, we figured no one wants another web app to log into so we let administrators define access workflows in Terraform and let developers request and gain access via Slack. That seemed to pay off: being code-based was a big plus for our early customers since it let them manage the logic in version control and test in CI/CD. Second, we knew that updating permissions/roles/access was a major source of toil and risk in the world of cloud infrastructure. Have you ever tried to avoid annoying, persistent access requests by setting policies that are a bit more permissive than you’d like? We felt that fully automated just-in-time access + approvals could really help here. But we also knew that a simple approval tool could end up leading to request fatigue - kind of defeating the purpose. So we built an SDK to let you define checks in code (e.g. pagerduty.on_call, okta.is_user_in_group, github.get_repo_collaborators) in order to dynamically route requests or fast-track access when appropriate. This seems to be paying off: users are creating Slack-based approvals in front of different types of risky actions like production access, sensitive queries and triggering Lambdas. We’d love your feedback on our approach so far. Does this make sense to you? Is this a tool you'd use? What would you want to see out of it? To learn more, check out the video that Nick (nmeans (Sym VPEng)) made [1]. You can also check out our docs [2] or set up your own flow [3]. thanks! -adam [1] https://ift.tt/8VOEJhq [2] https://docs.symops.com [3] https://ift.tt/DLVqkRP
21 by abuggia | 2 comments on Hacker News.
Hello HN, My cofounder (jon918) and I started Sym three years ago because we were frustrated with how hard it was to manage access to cloud infrastructure. We wanted to build a tool for JIT access that was actually designed for developers. We were wary of tools that tried to accommodate both devs and IT but ended up with usability compromises for both. First, we figured no one wants another web app to log into so we let administrators define access workflows in Terraform and let developers request and gain access via Slack. That seemed to pay off: being code-based was a big plus for our early customers since it let them manage the logic in version control and test in CI/CD. Second, we knew that updating permissions/roles/access was a major source of toil and risk in the world of cloud infrastructure. Have you ever tried to avoid annoying, persistent access requests by setting policies that are a bit more permissive than you’d like? We felt that fully automated just-in-time access + approvals could really help here. But we also knew that a simple approval tool could end up leading to request fatigue - kind of defeating the purpose. So we built an SDK to let you define checks in code (e.g. pagerduty.on_call, okta.is_user_in_group, github.get_repo_collaborators) in order to dynamically route requests or fast-track access when appropriate. This seems to be paying off: users are creating Slack-based approvals in front of different types of risky actions like production access, sensitive queries and triggering Lambdas. We’d love your feedback on our approach so far. Does this make sense to you? Is this a tool you'd use? What would you want to see out of it? To learn more, check out the video that Nick (nmeans (Sym VPEng)) made [1]. You can also check out our docs [2] or set up your own flow [3]. thanks! -adam [1] https://ift.tt/8VOEJhq [2] https://docs.symops.com [3] https://ift.tt/DLVqkRP
New Show Hacker News story: latest news
Show HN: Tabby – A Self-Hosted GitHub Copilot
21 by wsxiaoys | 7 comments on Hacker News.
I would like to introduce Tabby, which is a self-hosted alternative to GitHub Copilot that you can integrate into your hardware. While GitHub Copilot has made coding more efficient and less time-consuming by assisting developers with suggestions and completing code, it raises concerns around privacy and security. Tabby is in its early stages, and we are excited to receive feedback from the community. Its Github repository is located here: https://ift.tt/XlfAU4J . We have also deployed the latest docker image to Huggingface for a live demo: https://ift.tt/hrpF4ON . Tabby is built on top of the popular Hugging Face Transformers / Triton FasterTransformer backend and is designed to be self-hosted, providing you with complete control over your data and privacy. In Tabby's next feature iteration, you can fine-tune the model to meet your project requirements.
21 by wsxiaoys | 7 comments on Hacker News.
I would like to introduce Tabby, which is a self-hosted alternative to GitHub Copilot that you can integrate into your hardware. While GitHub Copilot has made coding more efficient and less time-consuming by assisting developers with suggestions and completing code, it raises concerns around privacy and security. Tabby is in its early stages, and we are excited to receive feedback from the community. Its Github repository is located here: https://ift.tt/XlfAU4J . We have also deployed the latest docker image to Huggingface for a live demo: https://ift.tt/hrpF4ON . Tabby is built on top of the popular Hugging Face Transformers / Triton FasterTransformer backend and is designed to be self-hosted, providing you with complete control over your data and privacy. In Tabby's next feature iteration, you can fine-tune the model to meet your project requirements.
New Show Hacker News story: latest news
Show HN: I feed all my daily entries to an AI (ChatGPT)
5 by drsmog | 1 comments on Hacker News.
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/LoUVx6l 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/xkJubIY .If I can get 100 people on the waitlist in the next few days, I'll launch the app!
5 by drsmog | 1 comments on Hacker News.
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/LoUVx6l 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/xkJubIY .If I can get 100 people on the waitlist in the next few days, I'll launch the app!
New Show Hacker News story: latest news
Show HN: Create AI Art with your phone (Android app, Stable Diffusion)
2 by liuxiaopai | 0 comments on Hacker News.
2 by liuxiaopai | 0 comments on Hacker News.
Wednesday, 5 April 2023
New Show Hacker News story: latest news
Show HN: AI-Less Hacker News
10 by sakras | 5 comments on 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.
10 by sakras | 5 comments on 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.
New Show Hacker News story: latest news
Show HN: Want something better than k-means? Try BanditPAM
4 by motiwari | 0 comments on Hacker News.
Want something better than k-means? I'm happy to announce our SOTA k-medoids algorithm from NeurIPS 2020, BanditPAM, is now publicly available! `pip install banditpam` or `install.packages("banditpam")` and you're good to go! k-means is one of the most widely-used algorithms to cluster data. However, it has several limitations: a) it requires the use of L2 distance for efficient clustering, which also b) restricts the data you're clustering to be vectors, and c) doesn't require the means to be datapoints in the dataset. Unlike in k-means, the k-medoids problem requires cluster centers to be actual datapoints, which permits greater interpretability of your cluster centers. k-medoids also works better with arbitrary distance metrics, so your clustering can be more robust to outliers if you're using metrics like L1. Despite these advantages, most people don't use k-medoids because prior algorithms were too slow. In our NeurIPS 2020 paper, BanditPAM, we sped up the best known algorithm from O(n^2) to O(nlogn) by using techniques from multi-armed bandits. We were inspired by prior research that demonstrated many algorithms can be sped up by sampling the data intelligently, instead of performing exhaustive computations. We've released our implementation, which is pip- and CRAN-installable. It's written in C++ for speed, but callable from Python and R. It also supports parallelization and intelligent caching at no extra complexity to end users. Its interface also matches the sklearn.cluster.KMeans interface, so minimal changes are necessary to existing code. PyPI: https://ift.tt/SEzGTuF CRAN: https://ift.tt/7txzLc0 Repo: https://ift.tt/TxCkoVp Paper: https://ift.tt/1EABaqN If you find our work valuable, please consider starring the repo or citing our work. These help us continue development on this project. I'm Mo Tiwari (motiwari.com), a PhD student in Computer Science at Stanford University. A special thanks to my collaborators on this project, Martin Jinye Zhang, James Mayclin, Sebastian Thrun, Chris Piech, and Ilan Shomorony, as well as the author of the R package, Balasubramanian Narasimhan. (This is my first time posting on HN; I've read the FAQ before posting, but please let me know if I broke any rules)
4 by motiwari | 0 comments on Hacker News.
Want something better than k-means? I'm happy to announce our SOTA k-medoids algorithm from NeurIPS 2020, BanditPAM, is now publicly available! `pip install banditpam` or `install.packages("banditpam")` and you're good to go! k-means is one of the most widely-used algorithms to cluster data. However, it has several limitations: a) it requires the use of L2 distance for efficient clustering, which also b) restricts the data you're clustering to be vectors, and c) doesn't require the means to be datapoints in the dataset. Unlike in k-means, the k-medoids problem requires cluster centers to be actual datapoints, which permits greater interpretability of your cluster centers. k-medoids also works better with arbitrary distance metrics, so your clustering can be more robust to outliers if you're using metrics like L1. Despite these advantages, most people don't use k-medoids because prior algorithms were too slow. In our NeurIPS 2020 paper, BanditPAM, we sped up the best known algorithm from O(n^2) to O(nlogn) by using techniques from multi-armed bandits. We were inspired by prior research that demonstrated many algorithms can be sped up by sampling the data intelligently, instead of performing exhaustive computations. We've released our implementation, which is pip- and CRAN-installable. It's written in C++ for speed, but callable from Python and R. It also supports parallelization and intelligent caching at no extra complexity to end users. Its interface also matches the sklearn.cluster.KMeans interface, so minimal changes are necessary to existing code. PyPI: https://ift.tt/SEzGTuF CRAN: https://ift.tt/7txzLc0 Repo: https://ift.tt/TxCkoVp Paper: https://ift.tt/1EABaqN If you find our work valuable, please consider starring the repo or citing our work. These help us continue development on this project. I'm Mo Tiwari (motiwari.com), a PhD student in Computer Science at Stanford University. A special thanks to my collaborators on this project, Martin Jinye Zhang, James Mayclin, Sebastian Thrun, Chris Piech, and Ilan Shomorony, as well as the author of the R package, Balasubramanian Narasimhan. (This is my first time posting on HN; I've read the FAQ before posting, but please let me know if I broke any rules)
Subscribe to:
Posts (Atom)