Show HN: New AI team mate who knows everything about your porjects: MagicAI https://bit.ly/45PQzcu

Show HN: New AI team mate who knows everything about your porjects: MagicAI Magic AI is a powerful knowledge hub platform that allows teams to centralize and index their data from various sources such as PDFs, Word documents, Excel spreadsheets, PowerPoint presentations, Google Drive, Google Docs, Google Slides, Notion, and even websites. This means no more scattered repositories or endless searching for information across different platforms. With Magic AI, everything is organized and easily searchable in one place. Magic AI is backed by ChatGPT, so you can ask questions about your documents. It will answer according to your documents and will give you the sources. It also allows you to invite your team mates with no extra cost. You can try it for free and cancel it anytime. https://bit.ly/42vzId7 June 7, 2023 at 12:00PM

Show HN: Castled Data – Customer engagement software on top of data warehouses https://bit.ly/3WTWRE0

Show HN: Castled Data – Customer engagement software on top of data warehouses Hi HN, We're Frank, Abhilash, and Arun from Castled Data(https://bit.ly/3qvfmma). Castled is a Customer Engagement platform built directly on top of cloud data warehouses like Snowflake, BigQuery, Redshift, and Postgres. In essence, Castled is identical to Braze and Iterable with a crucial difference - we don't keep a copy of your customer data. Instead, we enable marketers to create audiences directly on their cloud data warehouse and engage them across channels like Email, Sms, WhatsApp, Push, and In-app notifications - no SQL knowledge, no engineering favours required. Here is a quick demo: https://bit.ly/3P06Gyh We started our journey by building an open-source Reverse ETL solution to make warehouse data actionable to marketers. However, after talking to 100s of marketers, we realised that modern B2C marketers needed to leverage billions of customer data points from the data warehouse to run personalised marketing campaigns. While Reverse ETL could sync all this data to marketing tools like Braze, Iterable, etc., the traditional marketing solutions were fundamentally not designed to store and process so much data. That's when we changed course to build a warehouse-first customer engagement solution. With Castled, marketers could finally use "all" the data from their data warehouse to engage their customers without any tradeoffs. Customer Engagement platforms have historically been built on top of transactional databases. So, solving the same use cases on top of a data warehouse optimised for analytical workloads was a significant challenge. But fortunately, B2C marketing use cases primarily warranted bulk data access, which data warehouses were uniquely designed to solve. The architectural change also enabled us to offer capabilities that were impossible with traditional solutions. As Castled is a "headless" platform - meaning we don't store any customer data - we offer a pricing model based solely on the number of team members using our platform, not the volume of data processed. The approach allowed our customers to focus on marketing efficiency without worrying about the fluctuating costs associated with data usage. We have been building Castled for more than a year and have enabled many businesses to overcome the data limitations of existing marketing platforms. If you have a data problem in marketing, feel free to sign up and try our product for free - no credit card required. We have our solution hosted at https://bit.ly/3qvfmma. We have been avid followers of HN for years now. So we look forward to your thoughts, insights, questions, and concerns about our product in the comments below. I will monitor the thread throughout the day to answer questions from the community. Also, feel free to reach out to me personally at arun@castled.io. June 7, 2023 at 03:01PM

Show HN: Leaked system prompts (e.g.: GitHub-copilot chat, Microsoft-Bing chat) https://bit.ly/3J2SbpD

Show HN: Leaked system prompts (e.g.: GitHub-copilot chat, Microsoft-Bing chat) https://bit.ly/43L8wan June 7, 2023 at 01:00PM

Show HN: Stratup.ai – Startup Idea Machine https://bit.ly/43pc7eH

Show HN: Stratup.ai – Startup Idea Machine https://bit.ly/43uSgL8 June 7, 2023 at 12:34PM

Show HN: Homelab Monitoring Setup with Grafana https://bit.ly/3qAUTfx

Show HN: Homelab Monitoring Setup with Grafana https://bit.ly/43wTmG3 June 7, 2023 at 11:52AM

Show HN: AI Generated Travel Site https://bit.ly/43r6NY6

Show HN: AI Generated Travel Site Had some fun with GPT4 and Midjourney and created a travel website with bite-sized information for every city above 100k population. Let me know what you think! https://bit.ly/43qfj9T June 7, 2023 at 07:08AM

Show HN: Train Your Own Language Model on Your Favourite Programming Language https://bit.ly/3NiSsHH

Show HN: Train Your Own Language Model on Your Favourite Programming Language In the context of the Deep Learning class at Tsinghua University, my teammates and I have trained our own (tiny) LLM on Go code using the `go/scanner` tokens as the tokenizer! If you're ever looking to train a single-GPU Language Model over the weekend on your favorite Programming Language, feel free to use our code and VSCode Extension. https://bit.ly/45Sts0U June 7, 2023 at 04:32AM

Show HN: Swipes AI – Easily more attractive photos to get more swipes on Tinder https://bit.ly/45Mm8UG

Show HN: Swipes AI – Easily more attractive photos to get more swipes on Tinder https://bit.ly/3P1b6F5 June 6, 2023 at 05:36PM

Show HN: Serverless OLAP with Seafowl and GCP https://bit.ly/3CfMwZC

Show HN: Serverless OLAP with Seafowl and GCP https://bit.ly/45RYrum June 6, 2023 at 05:18PM

Show HN: PDF AI – Speak to any document https://bit.ly/3oFBgmg

Show HN: PDF AI – Speak to any document https://bit.ly/3WTrFor June 6, 2023 at 11:19AM

Show HN: Open-source, MIT JavaScript crypto library behind Skiff Mail https://bit.ly/3MUDkyy

Show HN: Open-source, MIT JavaScript crypto library behind Skiff Mail https://bit.ly/3qqjEv0 June 6, 2023 at 01:59PM

Show HN: Dockerless, Elixir Web Application Using Podman and Plug https://bit.ly/42sKQXj

Show HN: Dockerless, Elixir Web Application Using Podman and Plug https://bit.ly/3qs2g9f June 6, 2023 at 07:06AM

Show HN: Roboduck, a GPT-powered Python debugger https://bit.ly/43m7oKD

Show HN: Roboduck, a GPT-powered Python debugger I made a python library that gives GPT4/chatGPT access to both your source code and current program state. If it suits your workflow better, you can also turn all your error messages into (optional) conversations: https://bit.ly/43prjIs https://bit.ly/3qr6qy9 June 5, 2023 at 04:33PM

Show HN: My structured editor for my language, a walkthrough https://bit.ly/3C97Qjv

Show HN: My structured editor for my language, a walkthrough Eyg is a functional language with: - Exhaustive typing, so a type checked program will never crash - Structural (not nominal typing), so there is never any need to write a type declaration - Effect types, built using row types. Row types are also used for Records and Unions - No syntax, there is no parser the public interface to the language is a JSON format of the Abstract Syntax Tree (AST), which makes the structural editor necessary. https://bit.ly/3X5LrgJ June 5, 2023 at 04:36PM

Show HN: SQLPage – Build Dynamic Websites with Just SQL Queries https://bit.ly/43FgAth

Show HN: SQLPage – Build Dynamic Websites with Just SQL Queries Hey Hacker News! I wanted to share the open source project I have been working on during the last year: SQLPage, a tool to build small web applications entirely in SQL. Building web applications with just SQL isn't as crazy as it seems. Most simple applications can be expressed declaratively as just data queries that fill pre-defined web components. I'd love to hear your feedback and thoughts on it. Would you potentially use it? How can it be improved? Website: https://bit.ly/43GhXYx Github: https://bit.ly/3qjG5BU Example app: https://bit.ly/43Llghp https://bit.ly/43GhXYx June 5, 2023 at 11:20AM

Show HN: Made a HN-themed Framer blog template for HN community https://bit.ly/45H8zpH

Show HN: Made a HN-themed Framer blog template for HN community https://bit.ly/43AbONS June 5, 2023 at 03:11PM

Show HN: Codespelunker a command line search tool with TUI and HTTP modes https://bit.ly/45YDRIK

Show HN: Codespelunker a command line search tool with TUI and HTTP modes https://bit.ly/3qvpcnS June 5, 2023 at 07:22AM

Show HN: FemtoGPT – Pure Rust implementation of a GPT language model https://bit.ly/45Ijn6J

Show HN: FemtoGPT – Pure Rust implementation of a GPT language model https://bit.ly/45JbBtp June 5, 2023 at 12:58AM

Show HN: Tiny Code Improver https://bit.ly/3NbgioB

Show HN: Tiny Code Improver Hey, fellow hackers! I'm excited to share my latest project, TinyCodeImprover, which has become an indispensable tool in my coding workflow. What is TinyCodeImprover? TinyCodeImprover leverages the power of GPT-4 to analyze and enhance your project files. By simply loading your code into the GPT-4 context, you can ask questions about your code, identify bugs, and even request GPT-4 to write code snippets across multiple files simultaneously. The Story Behind its Creation As a programmer, I frequently turn to GPT-4 for assistance with topics outside my expertise. However, I found the process of copying and pasting code snippets into the chat cumbersome and time-consuming. That's when I had an idea: a tool that seamlessly integrates GPT-4 into my coding environment. A month ago, during a flight from Bangkok to Dubai, I developed the first prototype of TinyCodeImprover. It allowed me to feed project files directly to GPT-4 and request code improvements based on my specifications! It even wrote a Readme for itself – quite mind-blowing! Refining the Process To maximize the effectiveness of TinyCodeImprover, I discovered the importance of employing a critical approach. I created special commands, ".critic" and ".resolver," to initiate self-reflection, enabling GPT-4 to identify its own mistakes in approximately 30% of cases. Since its inception, I've integrated TinyCodeImprover into four different projects, transforming error-fixing into an enjoyable experience, even when dealing with CSS challenges. It has proven useful not only for code but also for any type of text. https://bit.ly/3NbgjZH June 4, 2023 at 06:23PM

Show HN: Rarbg on IPFS https://bit.ly/3MNWkib

Show HN: Rarbg on IPFS https://bit.ly/3qpgUxV June 4, 2023 at 04:07PM