Show HN: Tool that uses GPT to translate text into executable commands https://bit.ly/42HRN84

Show HN: Tool that uses GPT to translate text into executable commands https://bit.ly/3lHrwGp March 25, 2023 at 01:31PM

Show HN: Kepler Book – A Way to Document and Share Errors https://bit.ly/40v80vq

Show HN: Kepler Book – A Way to Document and Share Errors Kepler is a website to explain code errors in a context-driven way, instead of scouring the internet for solutions to obscure programming errors? This is an experimental project. Inspired by the popular Stack Overflow and Val Town. Kepler-Book is a new platform that allows developers to easily write and document errors for others to read and understand the context. Most times i was tired of struggling with obscure programming errors and wish there was a better way to document and share our solutions, check out Kepler-Book today. The team behind the platform is eager to hear feedback from the Hacker News community and is committed to making Kepler-Book the go-to platform for documenting and sharing errors. https://bit.ly/3THnk66 March 25, 2023 at 11:44AM

Show HN: ChatGPT Plugins are a security nightmare https://bit.ly/42HeycA

Show HN: ChatGPT Plugins are a security nightmare https://bit.ly/3EB8Lec March 25, 2023 at 12:39PM

Show HN: ESER-32/Zuse Elektra emulator https://bit.ly/3ZkUoC6

Show HN: ESER-32/Zuse Elektra emulator https://bit.ly/3LRso63 March 25, 2023 at 10:03AM

Show HN: CommandClick: WebBrowser enforced by JavaScript and shellscript(Termux) https://bit.ly/3z7fCc8

Show HN: CommandClick: WebBrowser enforced by JavaScript and shellscript(Termux) CommandClick is low code android app making tool. On the surface, CommandClick is web browser. In fact, this is low code android app making tool. Surely, CommandClick can customize brosser But feature. Futher more, you can original android app by low code. Please check my readme! https://bit.ly/3FRe4qo March 25, 2023 at 05:28AM

Show HN: FTX Creditor – Confirm that the bankruptcy court has your claim https://bit.ly/42CSa3V

Show HN: FTX Creditor – Confirm that the bankruptcy court has your claim FTX Creditor is the easiest way to confirm that the bankruptcy court knows about your claim. Background: Last week, FTX published 1.3M anonymized user accounts in a Schedule F filing that lists the unsecured creditors they know about. 1.3M is a huge number, but it may be less than half of the total users FTX had. If your account is not listed, file a proof of claim with the bankruptcy court, or they may not treat you as a creditor (Federal Rules of Bankruptcy Procedure: Rule 3003). The data was uploaded as a series of PDFs, which makes it hard to find your claim, especially if you don’t remember the exact amounts you had and have to fuzzy match with cmd+f! We built FTX Creditor so that you can find your claim with the information you have. Features: - Find claims by: - Assets. If you remember having 4-5 BTC, 10-20 ETH, 0-100 SOL, you can filter 1.3M claims down to 4. - USD value. The face value of a claim is the account value on November 11, the day FTX filed for bankruptcy. You can exclude “Sam Coins” from the value calculation. The court may ignore the value of assets closely associated with SBF, such as FTT and SRM. - Customer code. - See the court document a claim was listed in. - Subscribe for notifications about events that may impact your claim, such as when the court sets the deadline to file a proof of claim. - Search for terms across all public court filings. Future Work: - Creditors who are interested in selling their claims can receive offers from buyers. - Explore aggregate statistics across accounts and assets. - FAQ on the most relevant parts of the bankruptcy process. FTX creditors, we got this! https://bit.ly/3z5UAdL March 24, 2023 at 09:42PM

Show HN: Lotus – open-source pricing engine https://bit.ly/3K5Gm2V

Show HN: Lotus – open-source pricing engine Hey HN! We discovered that no one innovates on pricing because every billing software is inflexible. Excited to share our progress with Lotus entering beta (full MIT license, https://bit.ly/3UvItPM ). New features: * backtest and run analysis comparing multiple plans * version pricing plans like you version code * Meter and aggregate usage flexibly with custom SQL * billing for usage-based pricing, hybrid, bespoke contracts * generate invoice pdfs or integrate with Stripe, Braintree, Netsuite, Salesforce * webhooks to send alerts when usage thresholds are high or build robust invoicing integrations * analyze margin and cost per customer All feedback is appreciated! If the project is especially relevant to you, reach out on our website. Check out our brand new self-serve demo here ( https://bit.ly/3WN8WdV ). Or self-host here ( https://bit.ly/3UvItPM ) and let us know what you think. https://bit.ly/3WN8WdV March 24, 2023 at 06:04PM

Show HN: Naja-Verilog – Structural Verilog Parser https://bit.ly/3lF8ZdT

Show HN: Naja-Verilog – Structural Verilog Parser https://bit.ly/3JIoaer March 24, 2023 at 01:02PM

Show HN: Alinor the Platform for Advanced Materials https://bit.ly/42AqoVD

Show HN: Alinor the Platform for Advanced Materials Hi YC, Tarek here, CTO and Co-Founder at Alinor. We just released our Omni update, the biggest one yet: https://bit.ly/3FKkRSL Alinor is an end-to-end platform for advanced materials. I have often found that when I say those words, is that I have to explain what advanced materials are. But I will skip that for this audience. Perhaps what you didn't know is that this is a $2 trillion industry, but over 99% of it remains offline. Alinor enables, scientists, engineers, and researchers to focus on what they do best: solving the world's biggest problems, by working on the cutting edge of materials and physical science. While we focus on selling their martials and enabling them to reach wider adaption. Alinor covers everything from initial inquiry to final invoice and everything in between. We do believe that nearly all problems the world is facing can be solved by advanced materials. Happy to answer any questions you might have, including what are advanced materials, just don't ask me to explain it in Arabic. Or maybe do that, I need to practice it more anyways! https://bit.ly/40AT2V1 March 24, 2023 at 09:07AM

Show HN: Hacker News Summarizer (Chrome Extension) https://bit.ly/3LOZQdw

Show HN: Hacker News Summarizer (Chrome Extension) Hey Hacker News community, We're excited to announce the launch of our new Chrome extension, "Hacker News Summarizer," which uses OpenAI API to summarize articles on Hacker News. It helps you quickly understand the key takeaways without reading the whole article. Plus, no login or confirmation is required to use it! Simply install the extension and click the "summary" link next to "comments" when you want to read an article. Disclaimer: Not all articles are summarised, or supported but we will change and try to support them later. Additionally, this extension is not affiliated with OpenAI or Hacker News. Chrome Extension: https://bit.ly/3lzKcIi... Try it out today and let us know what you think in the comments below! Thanks, The Hacker News Summarizer team https://bit.ly/40bKaFy March 24, 2023 at 11:48AM

Show HN: Unity AI Asset Generation https://bit.ly/40ajEwj

Show HN: Unity AI Asset Generation Hello HN - like a lot of programmers, I am really excited by everything going on with ChatGPT/DALL-E. I am a game developer by trade, and I think there is a lot of potential to change workflows for game development. I was very inspired by Keijiro Takahashi's prototypes for asset generation using OpenAI within Unity, so I tried to make a more generic means of generating text and image assets within the Unity Editor using OpenAI's APIs. I've been surprised by the success so far - it definitely has it's limits, but I think we have just begun to scratch the surface of the potential here. https://bit.ly/3LP0W90 March 24, 2023 at 07:29AM

Show HN: ChatGPT develops a Dungeons and Dragons multiplayer game https://bit.ly/3Zd3Rv6

Show HN: ChatGPT develops a Dungeons and Dragons multiplayer game https://bit.ly/42DYmZg March 24, 2023 at 02:55AM

Show HN: Datapane – A new way to build reports, dashboards, and apps in Python https://bit.ly/3n9n2sp

Show HN: Datapane – A new way to build reports, dashboards, and apps in Python Hello HN! We’re Leo and Mandeep, founders of Datapane ( https://bit.ly/3JDfcPq ). We're building a way to create reports, dashboards, and web apps from your existing data using Python. Think of it as a combination of React and htmx, specifically designed for the Python data stack. Our GitHub is https://bit.ly/3Z9tLQn and you can try building a report or app in ~2 minutes on Codespaces: https://bit.ly/40vuRHu We started building Datapane at our previous start-up, where we struggled to deliver ML model results to clients. Much to our surprise, the data science took less time than repeatedly creating reports by copying and pasting plots into PowerPoint decks. It seemed absurd that we had to switch to PowerPoint or legacy BI tools like Tableau to share, and our initial goal was to programmatically generate reports using the datasets and plots we had in Python. To enable this, we started hacking on a Python-based UI framework for constructing HTML views from data-centric blocks – like plots, data tables, and layout components. You can export these to standalone HTML files, or host them as a web app on somewhere like GitHub Pages or Fly.io. We recently also added the ability to connect Python functions to forms and front-end events so you can build web apps which run backend code. We handle the entire network and RPC layer, so you only need to write plain Python functions that take parameters and return other blocks. You can check out an example of the code to create a simple app: https://bit.ly/3Zaqroj... Datapane’s philosophy is pretty different from other products in the space. We wanted to keep things simple, but avoid the footguns our users faced with frameworks like Streamlit, where the reactive/network-aware model was hard to move beyond an MVP or POC. For backend interactivity, we believe the original web got a lot right, and unlike reactive models which rely on websockets, Datapane is unashamedly request/response. This takes inspiration from HTTP and our own experiences with htmx, which offers an elegant way to add interactivity to HTML. Under the hood, we actually compile down to a (gasp!) XML-based hypermedia format, akin to HTML, but tailored specifically for constructing data UIs. The result is that not every change in your app requires a server round trip, as much of it can be pre rendered and most interactivity happens on the client-side. In addition to improving performance, this also makes running in production become 10x simpler. This separation between the view and backend compute also makes Datapane modular. If our app server isn’t a good fit for your use-case, serve Datapane views from the web-framework of your choice (we’ve been hacking on serving views from Django). Want to compute blocks from inside Airflow or generate them on a schedule or from a webhook? Computation can happen out of band of the UI. You can even build and host apps from inside of Jupyter, where you can preview blocks live and convert notebook cells to blocks in your view. We currently offer a hosting platform on https://bit.ly/3JDfcPq for sharing reports publicly (free) or with your team (paid), and will be adding serverless app hosting support to it in the next few weeks. Our ultimate goal is to create an open-source toolkit for building data products across the entire stack – from reports, to dashboards, to full-stack apps – all using 100% Python. You can see a few we’ve built already in our gallery: https://bit.ly/40wD3ag We’d love to hear your feedback. Thanks! March 23, 2023 at 02:50PM

Show HN: CodeAlpaca – Instruction following model for code https://bit.ly/3Jx83A0

Show HN: CodeAlpaca – Instruction following model for code https://bit.ly/3n5J8vW March 23, 2023 at 05:24PM

Show HN: Tripnotes.ai: Intelligent Travel Planner https://bit.ly/3FLTO9t

Show HN: Tripnotes.ai: Intelligent Travel Planner Hey HN, We're excited to announce the public beta preview of Tripnotes, an intelligent travel planner that mixes a custom recommendation engine, our own data, and a bit of GPT to help you find the right places to go while traveling. Our team has been working hard on this project for 6 months, and we're excited to finally share it with the HN community. With Tripnotes, you can keep track of all your notes about travel when planning to visit a city. Paste in article URLs, videos, emails, text messages, any other text, and if you need some help with research, ask our Concierge which will provide useful recommendations and itineraries for the city in question - with a fallback to GPT for things we didn't quite understand. If you're not ready to dive right in, here are a few short highlight videos: https://twitter.com/matthewer/status/1619047755271536640 https://twitter.com/matthewer/status/1621172173598756864 https://twitter.com/matthewer/status/1623703548545445890 https://twitter.com/matthewer/status/1638010661694234625 All the places by Tripnotes are from our own database, but we rely upon GPT to understand the intent of the incoming prompts, as well as to help with the prose in our response to ensure the place descriptions fit what's being asked for. Since we tweeted about our preview release on Monday, we've had over 15,000 people come and try at least one prompt, with over 40,000 unique notes generated from prompts about cities all over the world. We'd love for you to give Tripnotes a try and let us know what you think. The "unauthed" version is open to everyone. If you're interested in using the full version, please join our waitlist. The full version maintains a history of your notes and allows you to edit the text and auto-highlights any text you write/paste in on the fly, which can be useful for pasting recommendations from friends (say via SMS or Email) and having them auto-highlighted and mapped. You can also paste in links from articles, websites, blogs, even Tiktok or Youtube. We scrape those urls, gather the list of places that are mentioned, and then show them on the map along side the rest of your note. We'd love to hear your thoughts and feedback, so please feel free to leave a comment or reach out to us directly. Thanks for your support! https://bit.ly/3FN0kNj March 23, 2023 at 04:35PM

Show HN: Web demo of 13B Alpaca-LLaMA trained on improved Stanford dataset https://bit.ly/3LLcMkG

Show HN: Web demo of 13B Alpaca-LLaMA trained on improved Stanford dataset https://bit.ly/3TCAv8h March 23, 2023 at 12:35PM

Show HN: Remove “GPT” from your HN feed https://bit.ly/3TEDGw9

Show HN: Remove “GPT” from your HN feed https://bit.ly/3TGGkSb March 23, 2023 at 02:01PM

Show HN: Gyeeta – An Open Source and Free Observability Tool https://bit.ly/3n98o4x

Show HN: Gyeeta – An Open Source and Free Observability Tool Hello Everyone, We are excited to announce the public release of Gyeeta - https://bit.ly/3n98p8B Gyeeta is a free, eBPF based Open Source (GPLv3) Observability tool which provides the following capabilities : - Service Level Statistics such as Queries/sec (Requests/sec), Response Times (Latency) and HTTP Errors (if HTTP based) with no manual inputs or integrations. Monitors binary / proprietary network protocol or non HTTP Service statistics as well. - Service Maps, Process and Host level Network Flows with info on all Services and Processes. - Detection of Host and Process Level CPU starvation, Virtual Memory or IO Bottlenecks. - Monitor all applications without any instrumentation or tapping irrespective of the programming language used. - Self Learning Algorithms that can detect Anomalies, Contention or Degradation without any manual inputs. - Advanced Cluster, Service or Process Level Alerts using a powerful Web UI or REST APIs. - All Data In-House (On Prem). Not a SaaS tool. - All Linux Kernels released since 2016 supported (Linux Kernels v4.4.x or higher). Gyeeta is optimized (C++ based) for minimal CPU and Memory requirements. Website : https://bit.ly/3n98p8B Github link https://bit.ly/407cZmk https://bit.ly/3n98p8B March 23, 2023 at 08:56AM

Show HN: Wrapper around restic for Docker Compose https://bit.ly/40qjqRh

Show HN: Wrapper around restic for Docker Compose auto-restic is a tool for automatic backup and restore persistent data in docker compose. It uses restic under the hood but offers scheduled jobs, web notifications, and automatic recover (volume is empty and there is backup in cloud) if needed. https://bit.ly/3n7GaHf March 23, 2023 at 01:41AM

Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA https://bit.ly/402veJE

Show HN: ChatLLaMA – A ChatGPT style chatbot for Facebook's LLaMA ChatLLaMA is an experimental chatbot interface for interacting with variants of Facebook's LLaMA. Currently, we support the 7 billion parameter variant that was fine-tuned on the Alpaca dataset. This early versions isn't as conversational as we'd like, but over the next week or so, we're planning on adding support for the 30 billion parameter variant, another variant fine-tuned on LAION's OpenAssistant dataset and more as we explore what this model is capable of. If you want deploy your own instance is the model powering the chatbot and build something similar we've open sourced the Truss here: https://bit.ly/3FDGHaA We'd love to hear any feedback you have. You can reach me on Twitter @aaronrelph or Abu (the engineer behind this) @aqaderb. Disclaimer: We both work at Baseten. This was a weekend project. Not trying to shill anything; just want to build and share cool stuff. https://bit.ly/3lD6h8z March 22, 2023 at 10:07AM