Thursday, 14 November 2024

Show HN: I made a scam detector and build a public database for it https://bit.ly/4hKmkKb

Show HN: I made a scam detector and build a public database for it We think this is helpful because scams are getting more out of hand than ever, so we wanted to build a tool that can help people to identify scams instantly and ALSO creates a large dataset to "train" everyone's brain on scam detection patterns. After browsing 10-20 scams, anyone can quickly learn what indicators to look for in subtle (or not so subtle) scams. 1. Upload screenshot of anything you think is suspicious 2. GPT-vision goes to work, extract text and analyze the screentho and give you an instant result 3. Each upload adds to a growing public database, letting everyone to see and learn from real-world scam patterns. Try it out, contribute a recent scam that you've received lately, and hopefully this could help more people. https://bit.ly/3YQKcDn November 14, 2024 at 07:00AM

Wednesday, 13 November 2024

Show HN: Unifi – Accept Crypto Payments – Zero Transaction Fees https://bit.ly/4hMRaBO

Show HN: Unifi – Accept Crypto Payments – Zero Transaction Fees https://bit.ly/4hKDNSF November 14, 2024 at 01:44AM

Show HN: Building LLM Gameplay Mechanics with Guidance https://bit.ly/3Z2kAEx

Show HN: Building LLM Gameplay Mechanics with Guidance I've written this article about how I'm using small LLMs and logit_bias to leverage the gameplay mechanics of my generative visual novels engine. I also open sourced the guidance library as an npm package. https://bit.ly/3Z3Asqr November 13, 2024 at 11:30AM

Tuesday, 12 November 2024

Show HN: SurfSense – A Personal NotebookLM and Perplexity-Like AI with Privacy https://bit.ly/48PJ9b5

Show HN: SurfSense – A Personal NotebookLM and Perplexity-Like AI with Privacy https://bit.ly/3VcSnsH November 13, 2024 at 04:09AM

Show HN: ClearTerms – Analyze TOS of your Gmail-connected app https://bit.ly/3CoYYJL

Show HN: ClearTerms – Analyze TOS of your Gmail-connected app Hi everyone, I'm working on a SaaS idea to make TOS more understandable. Motivation: companies like Disney, Uber, and many more put an arbitration clause in order to protect themselves from being sued. Not to mention Adobe has also tried sneaking in access to users IP in their terms of service. Any feedback is appreciated, lmk if love the idea, hate it or anything in between! https://bit.ly/4fELeZC November 12, 2024 at 11:33PM

Show HN: We built the simplest Online Unit Converter for everyday use https://bit.ly/4fJnzY9

Show HN: We built the simplest Online Unit Converter for everyday use Features: 200+ unit converters in Area, Length, Mass, Speed, Temperature, and Time categories; Precision: up to 28 decimal places; Conversion formulas with examples; Neat UI with light/dark theme. Enjoy using it. https://bit.ly/4eu9a0Z November 12, 2024 at 02:53PM

Show HN: Chat-tree: a chat UI organized as a tree https://bit.ly/4fqfnfQ

Show HN: Chat-tree: a chat UI organized as a tree The problem with current chat interfaces is that they restrict the conversation to only a single thread. chat-tree is a tool that allows you to ask multiple independent follow-up questions without polluting the context or scrolling up and down through the chat history. https://bit.ly/4fmS1HU November 12, 2024 at 10:09AM

Show HN: Comicmark – A Self-hosted Link Manager with comic-like visual elements https://bit.ly/3ALwR71

Show HN: Comicmark – A Self-hosted Link Manager with comic-like visual elements https://bit.ly/3YN7bzb November 12, 2024 at 09:44AM

Monday, 11 November 2024

Show HN - All-in-one developer portfolio platform https://bit.ly/4epFlyr

Show HN - All-in-one developer portfolio platform Browse developer portfolios uploaded by real developers, upload your portfolio to be seen by others. https://bit.ly/3UMJ02A November 12, 2024 at 04:37AM

Show HN: Lyceum – An MMO game built with Zig and Erlang https://bit.ly/48JtwSx

Show HN: Lyceum – An MMO game built with Zig and Erlang Hey HN, this is a small project myself and closer friends have been building on our free time ( https://bit.ly/3YM6Ts2 ), it finally reached 0.1.0, we are open to feedback! The original idea was to experiment with Zig + Raylib, eventually we wrote a small server in Erlang as well. We started by first interacting with Erlang via its C bindings, but this eventually led to some of us to prototyping our own tooling to better integrate Zig types with Erlang, we called such tool "zerl" as its avaliable here https://bit.ly/3YM6TZ4 . Most of the developers are NixOS users, so the tooling heavily relies on Nix as well, including a Postgres running our devshell as well. https://bit.ly/3YM6Ts2 November 5, 2024 at 05:45PM

Show HN: Openkoda 2.0, an open-source insurance application platform https://bit.ly/3ULlMKc

Show HN: Openkoda 2.0, an open-source insurance application platform https://bit.ly/3Zb88CR November 11, 2024 at 10:57AM

Show HN: I made a conversation starter card game https://bit.ly/3YJb5ZR

Show HN: I made a conversation starter card game Hey HN, I made conversation starter game. Here's how it works: - Choose a theme like "Couples" or "Favorites" - Tap to reveal thought-provoking questions - Take turns answering and discover new things about each other I made ConvoCards because everyone has an interesting story to tell, but these don't often come up in day to day conversations. I also enjoy using them for journaling and self reflection. I hope you enjoy playing and learn something new about someone close to you! https://bit.ly/4fn9HD7 November 11, 2024 at 08:54AM

Sunday, 10 November 2024

Show HN: Krita RGBA Tech – Bringing Realistic Metal to Life in Open-Source Art https://bit.ly/3CnJPIH

Show HN: Krita RGBA Tech – Bringing Realistic Metal to Life in Open-Source Art Krita's v4.2+ RGBA brushtips let you paint with dimensionality, and it's a technology that Photoshop doesn't have (≖‿ゝ≖) It lets the creator do things like emulating light direction, making brushstrokes look 3D. I used them to make a set of metallic brushes. If there are any FOSS artists around, feel free to test them out. (p.s. Yes, I am learning Github so I probably made repository mistakes - apologies in advance lol) https://bit.ly/4enUuR1 November 11, 2024 at 03:45AM

Saturday, 9 November 2024

Show HN: Gleam.so – Beautiful OG images in seconds, no design skills needed https://bit.ly/4elG97z

Show HN: Gleam.so – Beautiful OG images in seconds, no design skills needed https://bit.ly/3YK03DC November 10, 2024 at 02:03AM

Show HN: Icon (AI Ads, icon.me, funded by Peter Thiel's Founders Fund) https://bit.ly/40GUbNZ

Show HN: Icon (AI Ads, icon.me, funded by Peter Thiel's Founders Fund) https://bit.ly/40Hkeom November 10, 2024 at 04:04AM

Show HN: LLM driven OS to execute network security exploration agents https://bit.ly/3O1S9jV

Show HN: LLM driven OS to execute network security exploration agents I made this thing where LLM works like a tiny OS kernel - it plans tasks and runs different agents. Right now it's doing security stuff (poking at networks, checking SSL, testing APIs) with WebGoat as a playground. The ultimate goal is to ask it "find vulnerabilities in XYZ" and see it orchestrate its own tools, backtrack, try different approaches, etc. The cool part is the LLM doesn't just blast out a bunch of tokens - it plans, reasons and executes tasks step by step during inference. Currently playing with security agents but you could plug in anything really. Would love getting you to play with it and maybe add an agent or two. https://bit.ly/3NZXkAK November 10, 2024 at 03:02AM

Show HN: Dracan – Open-source, 1:1 proxy with simple filtering/validation config https://bit.ly/4hKUi1d

Show HN: Dracan – Open-source, 1:1 proxy with simple filtering/validation config If you are tired of using Apache or Nginx to proxy your app and implement validation or limiting you may be interested in this hobbyist project. Thanks for all feedback. https://bit.ly/4hFtAXI November 10, 2024 at 01:15AM

Friday, 8 November 2024

Show HN: SICP-VSCode https://bit.ly/4fIfTWd

Show HN: SICP-VSCode I am sharing an opinionated configuration for VS Code that should suffice to work through Structure and Interpretation of Computer Programs (SICP). I have owned SICP for a decade or more and am giving it another go. I (re)started it last weekend using the DrRacket editor, which is fine, but I spend most of my time in vs code. It was a jarring to use another editor. So, in an evening of delightful bikeshedding, I now have a setup that should let me work through SICP in vs code. I thought I'd share this in case someone else is interested or has any feedback. This is a barebones configuration with a lightly tested installation script that works on my machine! I wanted to avoid installing a bunch of vs code extensions and was able to get this working with only a single extension to add scheme support to vs code. Any feedback is welcome and I hope someone gets some use out of this! https://bit.ly/4fGtT2u November 9, 2024 at 05:27AM

Show HN: I build a FullStack boilerplate to ship my projects faster https://bit.ly/48GA8Bk

Show HN: I build a FullStack boilerplate to ship my projects faster Every time I start a new project, it’s the same drill: setting up authentication, routing, databases, UI, etc. Sound familiar? I wasted 10+ hours on the same repetative setup. So I built Getstart, a SaaS-ready framework with everything you need to go from zero to launch—fast. It’s all here: NextAuth for easy auth Prisma + MongoDB for scalable databases Next.js API routes pre-built Nodemailer for emails Razorpay for both domestic and international payments Tailwind and Shadcn for sleek and customizable UI Let me know what you guys think and what can be improved https://bit.ly/48JZNsJ November 9, 2024 at 12:10AM

Show HN: RL Agent that can auto-optimize your LLM prompts https://bit.ly/3UFLWOr

Show HN: RL Agent that can auto-optimize your LLM prompts Hey everyone! Along with my team, I've developed a reinforcement learning system that automatically optimizes LLM prompts, complete with a visualization feature to track both prompt structure and learning progress over time. Take a look here: https://bit.ly/3YX9Ozo... Check out our website too: https://bit.ly/48Mo9lB In terms of how this visualization works: The RL Prompt Optimizer employs a reinforcement learning framework to iteratively improve prompts used for language model evaluations. At each episode, the agent selects an action to modify the current prompt based on the state representation, which encodes features of the prompt. The agent receives rewards based on a multi-metric evaluation of the model's responses, encouraging the development of prompts that elicit high-quality answers. And see our github repo! https://bit.ly/3XhrP9O https://bit.ly/3V7IeNV November 8, 2024 at 09:17PM