Show HN: Standardizing build, experiment, and deployment for LLM Development https://bit.ly/3L9xoBv

Show HN: Standardizing build, experiment, and deployment for LLM Development *Motivation* Hi hackers, I'm Asif. I know we dislike premature standardization, but hear me out. LLM Application development is extremely iterative, more so than most other types of application development. We need a process that allows us to iterate faster. LLM Development is highly iterative due to the activities that come with regular software development, as well as the need to make the LLM Application accurate and reduce hallucination. To improve hallucination, we need to trial and error various combinations of LLM models, prompt templates (e.g., few-shot, chain-of-thought), prompt context with different RAG architecture, and possibly try multi-agent architecture. There are thousands of permutations to try, and we want to be able to easily experiment with different permutations and have a process to objectively judge LLM performance so we can iteratively move towards accuracy goals. *Solution* I have been working in AI since 2021 - first at FAANG with ML, then with LLM in start-ups since early 2023. I have had the chance to talk with many different companies that have been successful and unsuccessful with AI development. Using my learnings, I am working on an Open Source framework to standardize the build, experiment, and deploy process for LLM Development. The goal of this framework is to optimize for rapid iteration. We are doing this by enforcing a modular LLM application layer build, allowing for easy testing of different configurations of your application. We provide maximum flexibility for using any external tools you want for building your application. We also have tools to benchmark your accuracy and improve the performance of your application in a data-driven way. Finally, everything is deployable through a Docker image. *Getting Involved* If you're curious, check us out on Github. You can get fully set up with a single command. Stars for better visibility https://bit.ly/4eIjUKw July 1, 2024 at 02:51AM

Show HN: AI Rapper Online – Generate Personalized Rap Songs with AI https://bit.ly/4bspGNA

Show HN: AI Rapper Online – Generate Personalized Rap Songs with AI We’re excited to share AI Rapper Online, a revolutionary platform that allows you to create personalized rap songs using advanced AI technology. Whether you’re an aspiring rapper, a music enthusiast, or just curious about AI's potential in music creation, our platform offers a unique and fun experience. Features include: Rap Generator: Input themes, styles, and keywords to create unique rap songs. AI Rapper Online: Generate full rap albums with custom cover art. https://bit.ly/4byk58A June 30, 2024 at 04:56AM

Show HN: Let Grumpy AI Roast Your Startup Idea https://bit.ly/4eNJv4T

Show HN: Let Grumpy AI Roast Your Startup Idea https://bit.ly/3VDx2I8 June 30, 2024 at 10:22AM

Show HN: I built a create-your-own-story interactive novel that runs with GPT https://bit.ly/3zqdM9F

Show HN: I built a create-your-own-story interactive novel that runs with GPT I built this project around a year ago, but I didn't really publicize it a lot. I do play with it every now and then and figured I should share it with you guys because I enjoyed it and hopefully you will as well. https://bit.ly/3xu8zwZ June 30, 2024 at 05:30AM

Show HN: Taarr, Shell Script Manager https://bit.ly/4ck32s1

Show HN: Taarr, Shell Script Manager Shell script manager inspired by rerun and other tools. Can be used for runbooks, deploys, hooks, C2, configuration management, and builds. Several improvements and updated site. https://bit.ly/45NirP0 June 29, 2024 at 06:43AM

Show HN: Auto-generate a custom, developer-first playground for your LLM app https://bit.ly/3xDvANR

Show HN: Auto-generate a custom, developer-first playground for your LLM app Hi everyone - We’re the team at Inductor ( https://bit.ly/3W3HWbF ), where we’re building the tools that developers need to build production-ready LLM apps and product features – far more quickly, easily, and systematically. We’re super-excited to share a new capability that we’ve just built: Custom Playgrounds. We built Custom Playgrounds because it’s important to be able to interactively experiment with an LLM app or product feature as you’re building it, and share your work in order to collaborate – but, today, this is too often cumbersome to do. Custom Playgrounds solve this problem by providing a developer-first way to auto-generate and instantly share a playground running directly against your code and environment, with a single Inductor CLI command: $ pip install inductor $ inductor playground my.module:my_function where “my.module:my_function” is the fully qualified name of a Python function that is the entrypoint to your LLM app. (No modifications to your code required!) Some highlights: Custom Playgrounds enable you to Instantly auto-generate a custom playground UI that is customized to your LLM app or feature. Run your playground directly against your code and environment, and securely use private data sources or internal systems. Iterate faster, with an easy, powerful way to interactively experiment with your LLM app and then systematically evaluate it when you’re ready (e.g., with hot-reloading, auto-logging, test suites, and more). Collaborate with other people (e.g., other teammates, including those who are less technical) by securely sharing your work, collecting feedback, and leveraging their expertise (for prompt engineering and more). See our docs if you're interested in learning more: https://bit.ly/4clycPG We also have a demo video in our blog post: https://bit.ly/3W5qmUJ You can try Custom Playgrounds out for free by just running the `playground` CLI command above – you’ll be prompted to create an Inductor account (for free) if you don’t already have one. Alternatively, if you’d like to create your account first, you can sign up here: https://bit.ly/4cj0Ssz (you’ll receive further “Getting started” instructions after you sign in). We’d love to get any feedback that you have, and are very happy to answer any questions - drop us a note in the comments! June 29, 2024 at 12:41AM

Show HN: Thermion, an open source 3D rendering toolkit for Flutter and/or Dart https://bit.ly/4cmF3YX

Show HN: Thermion, an open source 3D rendering toolkit for Flutter and/or Dart I'd like to share Thermion, an open source 3D rendering toolkit I made for Flutter and/or Dart. This came about when I needed a 3D renderer for a Flutter app[0] I was building. At the time, the only off-the-shelf option was to embed Unity, which wasn't ideal for a few reasons - unstable build process, compositing and transparency issues, and licensing uncertainty, just to name a few. In any event, frankensteining Unity (C#) together with Flutter (Dart) didn't seem like a great solution. After browsing for alternative renderers, I discovered Filament[1], an open-source, cross-platform Physically Based Rendering engine from Google. I initially only wrote some simple bindings to embed Filament inside a Flutter Android/iOS app, but have since added more functionality, and have expanded this to cover Windows, MacOS and Web (there was Linux support at one point, too, but I haven't been keeping up with it I'm afraid). Last week I published the first Thermion release to pub.dev[2], and with that milestone it seemed a good time to share with HN. This is also a call for contributors if anyone wants to help[3]. Some examples: - A live DartPad playground so you can try the Dart-only (i.e. non-Flutter version) of Thermion in browser (Chrome only for now). https://bit.ly/3znZZjN - My personal website, where I added an interactive clone of myself https://bit.ly/3W5kgUl - Prouder (a Flutter app from one of the Thermion contributors) https://apple.co/4cqKNkz https://bit.ly/4coFp1w https://bit.ly/4clznOS Happy to share more details if anyone is interested! [0] https://bit.ly/3zomcya [1] https://bit.ly/4cBdNGB [2] https://bit.ly/3zkdiBP [3] https://bit.ly/3zo00nR https://bit.ly/4clsKMI June 28, 2024 at 09:47AM

Show HN: AI-Powered Alerts When Your Brand Gets Mentioned in Newsletters https://bit.ly/4ckGWWi

Show HN: AI-Powered Alerts When Your Brand Gets Mentioned in Newsletters Hey HackerNews community! Excited to introduce my latest project: a game-changer for staying on top of your brand's mentions in newsletters – introducing AI-Powered Real-Time Alerts! As a founder, I know the struggle of keeping tabs on where your brand appears. Our solution uses cutting-edge AI to monitor newsletters in real-time. Whether it's a mention in industry updates or a spotlight in subscriber emails, our technology ensures you're always in the know. Here’s what sets it apart: Real-Time Alerts: Instant notifications when your brand is mentioned. AI-Powered Monitoring: Advanced algorithms that scan newsletters efficiently. Customizable Criteria: Tailor alerts to specific keywords or contexts that matter to you. The tool not only saves time but also ensures you never miss a beat in your brand's narrative. Try it out and transform how you manage your brand presence in newsletters. Your feedback is invaluable – let's innovate together! Check it out and share your thoughts! https://bit.ly/4ckyLZQ June 28, 2024 at 09:40AM

Show HN: A new social giving platform https://bit.ly/4cnbdDO

Show HN: A new social giving platform Picture this: you’re scrolling through your social media feed, feeling the usual blend of amusement and boredom until suddenly, a video catches your eye. It’s not just entertaining; it’s transformative. It inspires you, educates you, or maybe just brings a smile to your face when you needed it most. You’re filled with gratitude for the creator behind this masterpiece, but a simple “like” or “share” feels inadequate. You want to do more, to express your appreciation in a meaningful way. That’s where Public Gives sweeps in, offering a platform where your gratitude translates into real generosity on a global scale, tangible support for the creators who enrich your life. Readmore: https://bit.ly/4ckk1Ku... https://bit.ly/3SatCMf June 28, 2024 at 09:15AM

Show HN: PodNarrator – Have articles read to you in your favorite podcast app https://bit.ly/3VLyBUw

Show HN: PodNarrator – Have articles read to you in your favorite podcast app https://bit.ly/3XLOJb5 June 28, 2024 at 07:03AM

Show HN: Siram – Automate Watering Your Houseplants https://bit.ly/3xMKDVv

Show HN: Siram – Automate Watering Your Houseplants https://bit.ly/3VB5VNG June 27, 2024 at 04:45PM

Show HN: Code to run Gemini (Nano) locally on desktop/Chrome https://bit.ly/45YSPip

Show HN: Code to run Gemini (Nano) locally on desktop/Chrome Chrome Canary (nightly build for devs) now has Gemini LLM inbuilt. This is just some simple code/demo to enable and use that feature. https://bit.ly/3LmlYdT June 26, 2024 at 08:01PM

Show HN: Standard Webhooks – simplifying 3rd party API's https://bit.ly/3VIsoZn

Show HN: Standard Webhooks – simplifying 3rd party API's https://bit.ly/4cCXpVp June 27, 2024 at 01:24AM

Show HN: I built an indie, browser-based MMORPG https://bit.ly/45GSYqk

Show HN: I built an indie, browser-based MMORPG I've been working on an MMORPG that is now in alpha as a solo developer. Here are the major open source technologies that I use: Blender - 3D modeling software for creating the overall environment and every game object. I've gotten a lot of CC and Public Domain assets from https://bit.ly/45JAdT3 GLTF - I export assets from blender to the GLTF asset format JSON - I write a JSON config for every game object that describes things like its name, its interactions, its collisions, etc. Node.js exporter - I iterate over the environment and every asset to create a scene hierarchy. I use gltf-transform for processing all GLTF files, compressing them, removing redundancies, etc. Node.js server - Uses express and socket.io to process game state updates. It keeps track of every client's game state and issues delta's at each game tick (currently 600ms). The client can send interactions with different objects. The server validates those and updates the game state accordingly. HTML/CSS/JavaScript/Three.js client - I use regular web technologies for the UI elements and three.js for the 3D rending on the browser. The client is responsible for rending the world state and providing the client with different interactions. All code is written in JavaScript which means less context switching. Performance seems to be good enough, and I figure I can always optimize the server code in C++ if necessary. I am currently running two cheap shared instances but based on my testing, they can likely support about 200 users each. This is a low-poly browser based game so it should be compatible across many devices. The data a user needs to download to play, including all 3d assets, is approximately 2 MB, even though there are hundreds of assets. Overall, it's been a fun project. Web development and open source software have progressed to the point that this is no longer an incredibly difficult feat. I feel like development is going pretty well and in a year or so there will be plenty of good content to play. https://bit.ly/4bkTATF June 26, 2024 at 06:53PM

Show HN: Voice bots with 500ms response times https://bit.ly/4bldFJB

Show HN: Voice bots with 500ms response times Last year when GPT-4 was released I started making lots of little voice + LLM experiments. Voice interfaces are fun; there are several interesting new problem spaces to explore. I'm convinced that voice is going to be a bigger and bigger part of how we all interact with generative AI. But one thing that's hard, today, is building voice bots that respond as quickly as humans do in conversation. A 500ms voice-to-voice response time is just barely possible with today's AI models. You can get down to 500ms if you: host transcription, LLM inference, and voice generation all together in one place; are careful about how you route and pipeline all the data; and the gods of both wifi and vram caching smile on you. Here's a demo of a 500ms-capable voice bot, plus a container you can deploy to run it yourself on an A10/A100/H100 if you want to: https://bit.ly/4bkHQAS We've been collecting lots of metrics. Here are typical numbers (in milliseconds) for all the easily measurable parts of the voice-to-voice response cycle. macOS mic input 40 opus encoding 30 network stack and transit 10 packet handling 2 jitter buffer 40 opus decoding 30 transcription and endpointing 200 llm ttfb 100 sentence aggregation 100 tts ttfb 80 opus encoding 30 packet handling 2 network stack and transit 10 jitter buffer 40 opus decoding 30 macOS speaker output 15 ---------------------------------- total ms 759 Everything in AI is changing all the time. LLMs with native audio input and output capabilities will likely make it easier to build fast-responding voice bots soon. But for the moment, I think this is the fastest possible approach/tech stack. https://bit.ly/4bkHQAS June 26, 2024 at 10:51PM

Show HN: Chrome extension that brings Claude Artifacts for ChatGPT https://bit.ly/3xK2RqC

Show HN: Chrome extension that brings Claude Artifacts for ChatGPT Hey HN, I've made a Chrome extension called Artifacts for ChatGPT, which brings the Claude Artifacts feature to the official ChatGPT website. https://bit.ly/3VxsenC June 26, 2024 at 02:57AM

Show HN: Best Sales Day Ever for My Side Project – Notion Branding Kit https://bit.ly/3VHCzgD

Show HN: Best Sales Day Ever for My Side Project – Notion Branding Kit Hi HN, I’m excited to share that my side project, Notion Branding Kit, just had its best sales day ever with 468 new orders in a single day! That’s a staggering 46700% increase! It's been an amazing journey building this project, and seeing such a tremendous response is incredibly fulfilling. I’m happy to share the strategies and insights that led to this success. If you’re interested in how to achieve big sales days for your projects, let’s chat! https://bit.ly/3VBIP9X June 25, 2024 at 10:05PM

Show HN: ControlFlow – open-source AI workflows https://bit.ly/3xFQvzO

Show HN: ControlFlow – open-source AI workflows Hi HN! I’m excited to share ControlFlow, our new open-source framework for building agentic workflows. ControlFlow is built around a core opinion that LLMs perform really well on small, well-defined tasks and run off the rails otherwise. I know that may seem obvious, but the key insight is that if you compose enough of these small tasks into a structured workflow, you can recover the kind of complex behaviors we associate with autonomous AIs, without sacrificing control or observability at each step. It ends up feeling a lot like writing a traditional software workflow. With ControlFlow you: - define structured tasks for your agents to achieve, - assign one or more specialized agents to each task, - then compose the tasks into a workflow for execution. We've been working toward this for a while, applying insights from our work on Prefect (our workflow engine) and Marvin (our LLM framework). ControlFlow is our effort to bridge the gap between all those impressive AI demos and what we see B2B users actually trying to accomplish in production. More often than not, their goal is to sanely delegate a few steps of a workflow to an AI, not deploy a suite of end-to-end autonomous while loops. This is ControlFlow's initial release and we’d love your feedback. We hope it's a refreshing take on making LLMs feel like software again! You can check out the repo here: https://bit.ly/4cylRr1 https://bit.ly/3VU10c9 June 26, 2024 at 12:16AM

Show HN: Singulatron – On-Premise AI Platform https://bit.ly/4clH9bS

Show HN: Singulatron – On-Premise AI Platform https://bit.ly/4catUKO June 25, 2024 at 01:11PM

Show HN: I made a remote job board with a free CV maker tool https://bit.ly/45LRn2I

Show HN: I made a remote job board with a free CV maker tool https://bit.ly/4cBT70s June 25, 2024 at 09:57AM

Show HN: Qq: like jq, but can transcode between many formats https://bit.ly/4eF6Xks

Show HN: Qq: like jq, but can transcode between many formats qq is jq inspired interoperable config format transcoder with interactive querying. It features an optional interactive editor with autocomplete for structured data. And supports inputs and outputs for json, xml, ini, toml, yaml, hcl, tf, and csv to varying degrees of capability. https://bit.ly/45Ih3xc June 24, 2024 at 11:44PM

Show HN: All-in-one AI web assistant (open-source) https://bit.ly/3KYzwvU

Show HN: All-in-one AI web assistant (open-source) BrainyAI is a free Chrome browser extension that offers features such as AI chat aggregation, AI search, AI reading, and enhanced AI web browsing. (Free alternative to Sider and Monica). https://bit.ly/3KV4i8H June 24, 2024 at 03:49AM

Show HN: Field report with Claude 3.5 – Making a screen time goal tracker https://bit.ly/3VF9rqi

Show HN: Field report with Claude 3.5 – Making a screen time goal tracker https://bit.ly/3VyulaR June 24, 2024 at 02:30AM

Show HN: API for Internet Brand Data https://bit.ly/3VCopgT

Show HN: API for Internet Brand Data https://bit.ly/4eAYLBJ June 23, 2024 at 09:02PM

Show HN: A web app to automate content spinning for WordPress (not a plugin) https://bit.ly/3VDmQPH

Show HN: A web app to automate content spinning for WordPress (not a plugin) https://bit.ly/3KW14lr June 23, 2024 at 10:07AM

Show HN: Free open-source Chrome extension for users with disabilities https://bit.ly/3xC07LW

Show HN: Free open-source Chrome extension for users with disabilities Hello HN! Beginner dev here; read several articles about the challenges faced by users with disabilities (and the impact on businesses). Thought to build a chrome extension to enhance web experience for users with disabilities, after realizing that current solutions focus on auditing web for accessibility. Current features published on Chrome store: Text Magnification | High contrast | Alt text | TTS. Working on (but not published yet) tooltip to explain each feature, additional language support. Will appreciate feedback, collaborations and suggestions of things to improve. GitHub Repo: https://bit.ly/4bdxWkh https://bit.ly/3RB1uS3 June 23, 2024 at 09:12AM

Show HN: Online OPML editor to manage subscription lists https://bit.ly/4cft8fC

Show HN: Online OPML editor to manage subscription lists I made a small online editor to manage OPML[1] files easily. There are a lot of smart online editors for formats like JSON, but while OPML is supported by most subscriptions services, the experience of editing/managing it is poor outside of what each platform support. The pain of managing the file independently increases as the size of the OPML file grow larger. It's rather simple at the moment but the goal is to provide shortcuts for common desired tasks to make the experience of editing OPML much smoother and streamlined. The editor is a static website that runs locally in your browser, it doesn't require an account, nor do any tracking. Let me know your feedback or if you've any pain points around OPML GitHub repo: https://bit.ly/4cft93a Website: https://bit.ly/3XCDFgA [1] - https://bit.ly/3XCDGkE https://bit.ly/4cft93a June 21, 2024 at 02:13PM

Show HN: I built a Calendly integration that prevents no-shows https://bit.ly/3RIN5Dh

Show HN: I built a Calendly integration that prevents no-shows https://bit.ly/4ewTlb7 June 22, 2024 at 12:50PM

Show HN: I made tool that let's you see everything about any website https://bit.ly/3zaf5JM

Show HN: I made tool that let's you see everything about any website Yes, it's open source: https://bit.ly/4c8T4tt :) Why I'm building this? There are a lot of tools out there for discovering meta and security data relating to a website, IP or server. But currently, there isn't anything that does everything, all in one place and without a paywall/ user sign up. It's still a WIP, and I'm working on a new version, with some more comprehensive checks, so any feedback would be much appreciated :) https://bit.ly/4cdKvNP June 22, 2024 at 11:43AM

Show HN: I made a demo for my project management tool https://bit.ly/4cAnwwl

Show HN: I made a demo for my project management tool Hey Hackers, Last time I posted alot of the comments were asking about the posibility for a demo and maybe more reasoning on why someone should use the service. I have tried to implement some more things into the basic tier so that out of the box, the service is more unique with its use of AI. Anyway, there is now some new AI features as well and I've improved the existing features to ensure they have the right level of accuracy and creativity. Enjoy, Dan https://bit.ly/3z9MCDU June 21, 2024 at 11:07PM

Show HN: Good Tripper Guide – Discover Nearby History Powered by AI https://bit.ly/4eAARGS

Show HN: Good Tripper Guide – Discover Nearby History Powered by AI Good Tripper Guide, powered by AI, offers on-the-go insights into the history and intriguing tales of nearby landmarks. Kickstart your historical adventures on your next vacation! https://bit.ly/4bjfVRv June 20, 2024 at 08:35PM

Show HN: Local Voice Assistant Using Ollama, Transformers and Coqui TTS Toolkit https://bit.ly/3VQt00b

Show HN: Local Voice Assistant Using Ollama, Transformers and Coqui TTS Toolkit https://bit.ly/3XwTTrg June 20, 2024 at 11:48PM

Show HN: Directory of resources for learning German https://bit.ly/4cwaxf6

Show HN: Directory of resources for learning German https://bit.ly/3z5toPy June 20, 2024 at 11:30PM

Show HN: I Built a Non-AI Platform for Verified Deployment Scripts https://bit.ly/4c8o5O2

Show HN: I Built a Non-AI Platform for Verified Deployment Scripts I'm a solopreneur who has bootstrapped five tech startups over the last 10 years (all of them have failed). I've hated the time I've spent uploading the apps... Jesus Christ! A couple of months back, I spent 21.4 hours trying to configure a minimum-permission automated deployment script with Docker, Go, and Cloud Run. It was my first time with Google Cloud Run (I have past experience with AWS - EC2, SQS, DynamoDB, etc.). I remember fighting long days to set up AWS… But it happened again with GCP: 1. Fragmented documentation 2. Lack of examples 3. Strange, obtuse errors 4. Setting up service accounts was a nightmare. No wonder people go for admin rights and call it a day. 5. ChatGPT and Gemini were dancing around like headless chickens. No wonder wrapper services like Vercel are successful. But, I don't want wrapper services: - They don't have what I need - They can become very expensive - They don't give me control of the services I need (Escape Hatches) Seeing this gap, I'm sharing a platform that does things differently: - You manage your infrastructure (connect directly to the cloud provider) - Infrastructure code with tools like Pulumi is created for you. 100% verified. No AI hallucinations or sorcery. - Service accounts are created for you with minimum permissions - Pulumi is set up for you, connected with the deployment keys - The infrastructure will have all the dependent services chained together in the right order - It's idempotent. Run the script as many times as you want with no duplicates or side effects - Deletes are a single command - You can use these scripts as learning tools or examples I hope this can be useful to you as it is for me! Jose P.S. I'd love any feedback to make this product better! https://bit.ly/3KRXlFn June 20, 2024 at 12:06PM

Show HN: Umme.ai understands your codebase without LLM https://bit.ly/3zat8yP

Show HN: Umme.ai understands your codebase without LLM Hello HN! We are excited to introduce Umme.ai. Umme.ai is an innovative AI model designed to help developers understand, optimize, and transpile their codebases across various programming languages with ease. Umme represents a paradigm shift in AI understanding by redefining the AI experience. As innovation consultants, we faced the challenge of automatically rewriting complex legacy applications written in multiple programming languages. Current AI assistants like GPT or Claude aren't well-suited for most logical or automated tasks, and we couldn't rely on time-consuming prompt designs. Therefore, we built Umme for everyone. From a technological perspective: - Umme has an internal world model - Umme directly interprets multiple languages without relying on programming language syntax. Many products use custom build systems and macros, making it challenging to understand a codebase exclusively based on official programming language grammar. - No LLM, no neural net: While the industry is saturated with neural-first AI models, our vision sets us apart by adopting a logic-first approach ideal for automated tasks and workflows. - Focus on reasoning, not creativity: Our model prioritizes logical reasoning over creativity, which is why it's not based on LLMs or neural nets for understanding your codebase. - U programming language[2]: At its core, Umme leverages our proprietary programming language, U. More details on U will be shared soon. - Extensive benchmarks: We use extensive codebases such as Node.js, Chrome, LLVM, Java, and C# as benchmarks. Our goal is for Umme to be able to accurately rewrite these codebases. Umme is designed to understand our world, starting with your codebase. We’re still in the early stages and would love to hear your feedback and understand your use cases. Don't miss out, get your early access now! Or contact us: contact at umme.ai [1]: https://bit.ly/4cb3etA [2]: https://bit.ly/4caPVcs https://bit.ly/4cb3etA June 20, 2024 at 08:00AM

Show HN: MIT-Licensed High-Quality Video Game Built from Scratch with JavaScript https://bit.ly/3zk8Oej

Show HN: MIT-Licensed High-Quality Video Game Built from Scratch with JavaScript https://bit.ly/4b71FeB June 20, 2024 at 02:21AM

Show HN: Automate 80% of repeat writing and thinking tasks with Spiral https://bit.ly/3Vxq72X

Show HN: Automate 80% of repeat writing and thinking tasks with Spiral https://bit.ly/3xzSo0S June 19, 2024 at 04:52AM

Show HN: I made a simple hue/gradient game https://bit.ly/45x23lB

Show HN: I made a simple hue/gradient game Time-to-time, I create a simple small game I can play when I have a few minutes (wink-wink). Made with Angular (no particular reason other than it's the fastest way for me). Source: https://bit.ly/4ewroA4 https://bit.ly/4b3SlIw June 18, 2024 at 09:39PM

Show HN: I made an open source and local translation app https://bit.ly/3VKz2PY

Show HN: I made an open source and local translation app A few years ago, right after high school, I decided to try to make a simultaneous translation app for Android as a side project, it took longer than expected (about 2 years) and I had to make a lot of compromises (I had to use Google's API and therefore make users use a developer key because at the time there were no free solutions for speech recognition and translation that had good quality). At the end of university, I decided to pick it up again and finally, using OpenAi's Whisper for speech recognition and Meta's NLLB for translation (with both running locally on the phone), I managed to make it free and totally open-source (as it was meant to be from the beginning). The app is still in beta, so I would love your feedback. https://bit.ly/3VMGTMT June 18, 2024 at 10:26PM

Show HN: AI Site Generator with React and Tailwind CSS Components https://bit.ly/3VL6qWL

Show HN: AI Site Generator with React and Tailwind CSS Components https://bit.ly/3VWsRIZ June 17, 2024 at 11:28PM

Show HN: Assistants Hub – A Portal for Building AI Assistants https://bit.ly/4etgAms

Show HN: Assistants Hub – A Portal for Building AI Assistants Hello HN Folks, I started working on Assistants Hub to solve a personal need, creating math assistants for my 3rd and 7th graders. I wanted to see what they were asking the AI at the same time, also make it super easy to get to it (with a link I can bookmark on their Chromebooks) without signing up or remembering things. They liked it, and used it to learn concepts well I expanded on the idea and felt like GPTs and AI assistants are underutilized in many fields due to the technical barriers involved in creating and distributing them. Assistants Hub is an effort to democratize this process, enabling even non-tech savvy users to build and deploy AI assistants tailored to diverse needs and domains. Best of all it is Open Source - https://bit.ly/3z7kTDK Docs - https://bit.ly/3z6b9cV Web - https://bit.ly/3XqYbjW Here are some sample personal assistants you can try with a link Personal Motivator - https://bit.ly/3XLal7J... 7th Grade Math Tutor - https://bit.ly/3z9mw3N... Story Sprout - Kids Story Teller - https://bit.ly/4coiQcS... British Slang Converter - https://bit.ly/3z9mx7R... 2nd Grade Math Tutor - https://bit.ly/4coTqM3... Einstein Assistant - Tells you all about Dr.Einstein - https://bit.ly/4etgATu... Primary goal is to add transparency and controls to the buyer (person paying for the AI) at the same time, make it super easy for the consumer of the AI (students, customers, employees etc.,). Right now this has analytics, conversation history, visual customizations, integration options. Document support (RAG) is available with OpenAI assistants, Planning to introduce support for functions and more eventually. At some point I hope to build a wysiwyg editor to drag and drop functions, capabilities to customize AI Assistants Right now this support 4 major providers - OpenAI, Groq, Anthropic, and Google Gemini. Users can Bring Your Own API Keys (BYOK) from these platforms or use Assistants Hub's default key. Technical Stack: • Frontend: Next.js with Tailwind CSS and Flowbite for a clean, responsive design. • Backend: Prisma ORM on top of PostgreSQL ensures robust data handling. • Storage: AWS S3 for reliable blob storage. Do you like the idea / or skeptical of it? What could be improved or changed? I’m looking for honest, constructive feedback that can help refine and enhance the platform. Are there specific tasks or industries you think could benefit by Assistants Hub? I’m keen to explore new domains where this can make a significant impact. LOOKING for Contributors to this project, both technical and non-technical, feel free to reach out to me santthosh -at- gmail -dot- com https://bit.ly/4evrJDl June 18, 2024 at 04:12AM

Show HN: DBee – TUI Based Database Manager https://bit.ly/3xaE9Qd

Show HN: DBee – TUI Based Database Manager https://bit.ly/3Vp9mal June 17, 2024 at 09:29AM

Show HN: Make notion like illustrations with consistency and editability https://bit.ly/45sxYna

Show HN: Make notion like illustrations with consistency and editability Hi! Presenting MakeIllustrations, which helps you generate vector illustrations in consistent styles like Notion avatars, Corporate Memphis art, and Flat art. These are fully colorable and editable too :) While working on projects, we realized that there were very limited options for fully customizable illustrations that told the story of our brand. We tried some AI image generators online but faced issues with consistency and editability. These illustrations were also not available in vector format. So we decided to solve this problem. It offers: 1.) Consistent and Customisable illustrations in vector or raster form. 2.) Fully colorable and editable, so you can color them according to your brand style and delete paths as you wish. 3.) Export in PNG or SVG format with options to remove or preserve background. Feel free to check us out and give feedback, you can join our community at https://bit.ly/4c3KxHV. We are offering 3 free credits to anyone who signs up to play around with our product! https://bit.ly/4c3KA6z June 17, 2024 at 05:02AM

Show HN: Graphmark – Enhanced bookmarking service as Chrome extension https://bit.ly/4co4KYG

Show HN: Graphmark – Enhanced bookmarking service as Chrome extension https://bit.ly/4crGMw1 June 17, 2024 at 03:39AM

Show HN: Made this tool to promote my projects online https://bit.ly/3VKMiUX

Show HN: Made this tool to promote my projects online https://bit.ly/4b7i2ry June 17, 2024 at 12:33AM

Show HN: Paste2Download – No Login, No Ads, Download Videos Watermark Free https://bit.ly/3VoyRsb

Show HN: Paste2Download – No Login, No Ads, Download Videos Watermark Free Hi Hacker News, I'm excited to share Paste2Download, a web app that lets you download videos from various platforms like TikTok, YouTube, Instagram Reels, YouTube Shorts, Pinterest, and even 9Gag, all without watermarks. What it does: Paste2Download simplifies the process of downloading videos by allowing you to paste a video URL from multiple platforms and download the video directly to your device. It removes watermarks and supports a wide range of video sources. Why I built it: There are plenty of sites that can help with downloading videos from TikTok, but many of these websites are cluttered with banners and ads, making them slow and cumbersome to use. I wanted to create a tool that offers a seamless, ad-free experience. Paste2Download is designed to be super clean and fast, providing a hassle-free way to download videos. Feedback: I’d love to get your feedback! Let me know what you think, any suggestions, or if you encounter any issues. https://bit.ly/4eqfGXS June 16, 2024 at 06:05AM

Show HN: Alpha Demo of NotePad.ai (open source) https://bit.ly/3zbUW5L

Show HN: Alpha Demo of NotePad.ai (open source) Hi all, I threw together a small prototype I am calling “Notepad.ai”. A new take on UIs for interacting with LLMs. While I enjoy using LLM’s in the chat format I wanted to see what it would be like to do it in a more long form style. It let’s you write in a pretty free form, much like Window’s Notepad, but you can choose to hit ctrl+[ to analyze the text with a preset prompt of your choosing. It has a few other small features. It’s WIP and very experimental. I would appreciate any feedback or thoughts. Video: https://youtu.be/ntdlgFmSxQY Live Demo: https://bit.ly/45vh3QP Github repo: https://bit.ly/4ckmXq5 More of my Projects: https://bit.ly/45oP7Os Have a great rest of your weekend! https://bit.ly/4clVzrN June 16, 2024 at 12:15AM

Show HN: We Made The World's Smallest and Cheapest Network Switch https://bit.ly/3xmOusj

Show HN: We Made The World's Smallest and Cheapest Network Switch Hello, we're Max and Byran from MUREX Robotics, a high school robotics team from Exeter, New Hampshire. We are super proud to have made this open source piece of technology! I hope you like it. https://bit.ly/3xmOuZl June 16, 2024 at 03:26AM

Show HN: Collate multiple PDFs into one with cover and automatic TOC https://bit.ly/3RRBcez

Show HN: Collate multiple PDFs into one with cover and automatic TOC collatepdf is a quick-and-dirty Python script I wrote for my own needs to collate multiple PDFs into one (essentially for printing purposes) with the following features: * an optional cover page, * automatic table of contents generation with global page numbering, * automatic page resizing to ensure all pages in the collated PDF have the same dimensions, * an overlay bar on each page with the current file name and global page number. This is alpha-quality software (no tests, minimal documentation etc). Use at your own risks. Hope some will find it useful! https://bit.ly/3KQQLil June 15, 2024 at 05:59PM

Show HN: An open source extension to block large media brands from Google search https://bit.ly/4bXs140

Show HN: An open source extension to block large media brands from Google search Google sends 16 large media brands (588 individual brands) a combined 3 billion+ clicks per month. They rank first page on 85% of all searches. They are inundating the web with things like subpar product recommendations, AI written listicles, and cookie cutter reviews. I don't like that, so I made an open source extension that blocks all of them from search results. (I'm not a developer, and I made this with Claude Opus's help) https://bit.ly/4elSCcG June 15, 2024 at 05:02AM

Show HN: Summarize Trending GH Repos in Terminal or Browser https://bit.ly/3KL0eYy

Show HN: Summarize Trending GH Repos in Terminal or Browser Hey HN, I built a tool that fetches the daily trending GitHub repositories and uses GPT-4o to generate useful, detailed markdown-style summaries. The app then offers to render them in the terminal itself or as HTML, which is then opened your default web browser. I'm neither a trained programmer nor a computer science student, but I'm a geek nonetheless and had fun building this, so I wanted to share. Maybe it doesn't save anyone any time, but again, I had fun building it. Cheers! https://bit.ly/3XlqYGz June 15, 2024 at 02:23AM

Show HN: 100% open-source voice assistant – as a HAL9000 https://bit.ly/3KLMYCY

Show HN: 100% open-source voice assistant – as a HAL9000 It started in 2018 with my first 3D printer and some openscad designs - just something that looks like a HAL9000 (and had a controlled red LED for the visuals) - it ended up being a full software-project...that hasn't ended yet. But: it is at a (quality-)point at which I am OK with putting it up on stage. My project goals: A digital voice-assistant that is... - actually usable (response times, error rates, ...) - performs everything on-device ("look ma, no cloud") - is entirely Free/Libre Open-Source-Software - is as-easy-as-possible to build I consider all four goals to be accomplished even at this ~90% stage of the project. If you just want to get some quick impressions, check out the "Demos" (video-)page in the github wiki (prominently linked in the README in the github repo). If you want to spend some more time on this, it's probably easiest to watch my presentation at Hackaday Europe from two months ago: https://www.youtube.com/watch?v=oqJCU8FRMQg&t=14761s https://bit.ly/3VGZ1HZ June 15, 2024 at 01:27AM

Show HN: LLM grammar explainer and flash card maker for Japanese https://bit.ly/3z4q2fN

Show HN: LLM grammar explainer and flash card maker for Japanese Goal was to make it easy to jump from textbook learning into immersion. I wanted to play video games in Japanese, and started by using LLMs and a notebook, but figured it would be easier to streamline it all in an app. - You input a sentence in Japanese (easier on mobile where you can handwrite kanji you don't know) - App translates the sentence, explains the grammar, and gives you a list of flash cards - You choose some flash cards to save for studying later - You input a question about the explanation for more information - App explains some more and gives you more flash cards - Repeat And then you can review the flash cards later with the built-in SRS system. There's a video to explain the UI on the front page. https://bit.ly/4ekNWDU June 13, 2024 at 11:26PM

Show HN: Elles – A Nicer /Bin/Ls https://bit.ly/3RPyndZ

Show HN: Elles – A Nicer /Bin/Ls https://bit.ly/4cc7PLK June 13, 2024 at 11:58PM

Show HN: Freenet 2024 – a drop-in decentralized replacement for the web [video] https://bit.ly/3Rqvvns

Show HN: Freenet 2024 – a drop-in decentralized replacement for the web [video] https://www.youtube.com/watch?v=enTAromEeHo June 14, 2024 at 01:22AM

Show HN: Shpool, a Lightweight Tmux Alternative https://bit.ly/4b345uI

Show HN: Shpool, a Lightweight Tmux Alternative shpool is a terminal session persistence tool developed internally at google to support remote workflows, which we have open sourced. https://bit.ly/3zakFvp June 13, 2024 at 02:22PM

Show HN: Dive into Deep Work–Your Oasis, Your Way https://bit.ly/45ptZaN

Show HN: Dive into Deep Work–Your Oasis, Your Way Elevate your productivity with Oasis, the AI-powered ambiance generator. Customize your workspace with notes, timers, focus music, and sounds—all tailored to your liking. Create the perfect environment for deep focus and creativity. Try it for free and discover how unique your background can be! https://bit.ly/3Xn7pxz June 13, 2024 at 01:26PM

Show HN: We built an AI Copilot for end to end project development workflow https://bit.ly/4ej965j

Show HN: We built an AI Copilot for end to end project development workflow Omniflow creates, customizes and automates project workflow from requirement creation, tech design, dev scheduling to release and more. All done in 3 minutes. https://bit.ly/4eovHxi June 13, 2024 at 07:06AM

Show HN: I created a tiny web crawler for Python https://bit.ly/3RoIQwu

Show HN: I created a tiny web crawler for Python https://bit.ly/4b5wU9U June 13, 2024 at 01:41AM

Show HN: I gamified AI logo generation for better designs https://bit.ly/3VEBh7q

Show HN: I gamified AI logo generation for better designs I recently quit my job at a decent TTS company I was working for as a software developer advocate to pursue what I have always enjoyed doing, which is creating software that is helpful. Before and after quitting my job, I have always found it expensive and time-consuming to hire a designer that can come up with a decent logo for my software, and as a software engineer, I really enjoy coding, not designing. One day, I made a pretty bold move to design a logo, and it took me a whole day to come up with a logo that looks nice. This is the reason I built Owl AI, a logo generator that generates top-notch logos using GPT-4o and Dalle-3. With OwlAI, I was able to build reliable software that would make my life much easier by allowing me to focus on my specialty, which is coding and definitely not designing. OwlAI is available for everyone to try out. Give me your honest feedback, and I promise I will respond to every single comment and make improvements. https://bit.ly/3xgrcEq June 11, 2024 at 11:50PM

Show HN: AI Agent System to Analyze ArXiv AI Papers https://bit.ly/4ehF9ma

Show HN: AI Agent System to Analyze ArXiv AI Papers Building a multi-agent system to analyze new AI research papers from 3 distinct perspectives: - Deep learning researcher agent: extract interesting deep learning methods that are related to paper - Theoretical mathematician agent: figure out theoretical mathematical concepts that are important in this paper and additional theoretical references that will be useful in understanding it - Skeptic agent: find unjustified assumptions that lack supporting evidence For this mvp, I used low-code agent platform StackAI (YC W23) and wrote about my process: https://bit.ly/3yYDnGu... https://bit.ly/3xeBu7U June 12, 2024 at 03:53AM

Show HN: Collaborative ASCII Drawing with Telnet https://bit.ly/3VjKaSG

Show HN: Collaborative ASCII Drawing with Telnet https://bit.ly/3VmQ5pP June 10, 2024 at 02:58PM

Show HN: Epidemik a Python package for epidemic simulation https://bit.ly/3XkhHyB

Show HN: Epidemik a Python package for epidemic simulation Hi everyone, I'm happy to share `epidemik`, a Python package for epidemic modeling. Epidemik, currently supports: - Homogeneously mixed Model: Easily define compartmental models by just specifying the transitions and rates - Age Structure: Convert any compartmental model to an age-structured model by simply adding an age contact matrix and a the population of each age group - Network Model: Easily define epidemic models running over an arbitrary network structure - Meta-Population Models: Define metapopulation model In a previous life (circa 2008-2012), I worked as the leading developer for a large-scale epidemic model so when CoVID hit I wrote a series of blog posts (see https://bit.ly/3VCoQcd ) working through the mechanics of how this kind of model works. Epidemik is the result of all the code that got written during the lockdowns, and in the years since that, I finally cleaned up and decided to publish it in case others find it useful (perhaps as a teaching tool?) This is my first package, so feedback, comments and suggestions are definitely welcome. https://bit.ly/3XCZjkT June 11, 2024 at 08:11PM

Show HN: I combined gpt4 and tailwind to create a website builder for developers https://bit.ly/3Xi9wD5

Show HN: I combined gpt4 and tailwind to create a website builder for developers Hey HN, As a freelance web developer, I've been on the lookout for the perfect static site generator that prioritizes modern design, lightning-fast loading speed, and complete code ownership. I've grown increasingly frustrated with the limitations of popular website builders like Webflow and Framer. Sure, they make the design process easier, but when it comes to having full control over the source code and customizing every little detail, they just don't cut it. I was tired of being locked into walled gardens and dealing with bloated frameworks just to display a simple site. That's why I created InstaWebAI – a static site generator that harnesses the power of AI and Tailwind CSS to create stunning, responsive websites without the unnecessary baggage. With InstaWebAI, you can: Generate blazing-fast static sites from simple text input Enjoy a modern, sleek design right out of the box Customize every aspect of your site using Tailwind CSS Export your code and host it anywhere, ensuring complete control Benefit from a lightweight, self-contained solution without relying on external frameworks As a solo founder, I built InstaWebAI to address my own frustrations and needs as a developer. But I quickly realized that many of my fellow devs were facing the same challenges. InstaWebAI is designed to make your life easier, whether you're building a personal portfolio, a client project, or a complex web application. If you're a developer who values speed, control, and modern design, give InstaWebAI a try. I'd love to hear your thoughts, feedback, and suggestions. Your input is crucial in shaping the future of InstaWebAI and making it the go-to static site generator for developers like us. Thanks for checking out my project! Cheers, Brian Founder of InstaWebAI https://bit.ly/3WwkLap June 11, 2024 at 08:15AM

Show HN: Comparing various contrastive losses on text and vision embeddings https://bit.ly/4aWwjar

Show HN: Comparing various contrastive losses on text and vision embeddings https://bit.ly/3VjbXCz June 11, 2024 at 02:54AM

Show HN: Text2Infographic – AI Infographic Generator https://bit.ly/3Xj4YMD

Show HN: Text2Infographic – AI Infographic Generator https://bit.ly/3Xj50Ef June 10, 2024 at 08:32PM

Show HN: Summarize Anything, Forget Nothing https://bit.ly/4ehBhRZ

Show HN: Summarize Anything, Forget Nothing You likely forget 90% of the content you consume within a week. I built Recall to fix this. Recall summarizes online content, connects it in a knowledge graph and resurfaces it on a schedule tailored to your learning curve helping you remember the information you care about. https://bit.ly/3Xh5gDA June 10, 2024 at 11:05PM

Show HN: Turn any number into a complicated math expression https://bit.ly/3KxCG9E

Show HN: Turn any number into a complicated math expression Credit goes to the contributors of https://bit.ly/3VD4YpG for making the tool's core. https://bit.ly/3VANIkw June 9, 2024 at 11:00PM

Show HN: Using the djb2 hash to map IP addresses to readable words for the lulz https://bit.ly/4edgkYy

Show HN: Using the djb2 hash to map IP addresses to readable words for the lulz Hi HN, This is more or less a fun experiment that I thought was worth sharing. Using Daniel J. Bernstein's [1] djb2 hash that he made when he was only 20 years old in 1991, we map names to hashes and provide reverse mappings using an english word list from dwyl [2]. You can see it here: https://bit.ly/3V8V6Cs Hamon (ハモン not 刃文) is derived from HAsh MOdulo Name. I hope you like it [3]! [1] The Cypherpunk Super Hero, https://bit.ly/3Vh88Or [2] https://bit.ly/4b0DiiK [3] Probably minimal real life use cases. ¯\_(ツ)_/¯ June 10, 2024 at 01:23AM

Show HN: I Build an AI-Powered API That Instantly Obtains Website Information https://bit.ly/3VzKaiM

Show HN: I Build an AI-Powered API That Instantly Obtains Website Information I built SiteProfile(siteprofile.io) to simplify how we access detailed website information. The main feature of SiteProfile is that you can obtain all relevant website information with a single, simple API call. With one API call, you can immediately get the following information: 1.Real-time Webpage Screenshots Instantly capture real-time screenshots in both PC or Mobile views. 2. AI-Generated Content: Generate content based on user prompts and website data, e.g. Describe the core functions of this website. 3.Comprehensive Website Info: Social Media Links, Contact Info, Basic Details, and Assets, all in one place. With just this API, you can instantly create an ai directory or similar website. SiteProfile is currently in the testing phase. During this period, all subscriptions are discounted. There are still a few minor issues, and I’m working hard to fix them. If you try it out, please let me know if you found it useful, if you have anything you’d like me to add, or if you have any other feedback. And if you have any questions, I’d be happy to answer. Much appreciated. https://bit.ly/3XfIhJl June 10, 2024 at 02:17AM

Show HN: Clip2qr: displays whatever URL or file is in clipboard as a QR code https://bit.ly/3Rjq5KY

Show HN: Clip2qr: displays whatever URL or file is in clipboard as a QR code https://bit.ly/3yW76jm June 10, 2024 at 12:38AM

Show HN: A self-generalizing, hyperparameter-free gradient boosting machine https://bit.ly/3x8OZGe

Show HN: A self-generalizing, hyperparameter-free gradient boosting machine PerpetualBooster is a gradient boosting machine (GBM) algorithm which doesn't have hyperparameters to be tuned so that you can use it without needing hyperparameter optimization packages unlike other GBM algorithms. Similar to AutoML libraries, it has a budget parameter which ranges between (0, 1). Increasing the budget parameter increases predictive power of the algorithm and gives better results on unseen data. https://bit.ly/3Kyg3C3 June 9, 2024 at 09:02AM

Show HN: I Built My Product with Next.js After Getting Scammed by LegalZoom https://bit.ly/3Vfb6Tt

Show HN: I Built My Product with Next.js After Getting Scammed by LegalZoom Hi HN, When I was 16, three years ago, I got overcharged by LegalZoom for setting up an LLC. They made it seem more complicated than it is. You can actually do it yourself using your state's Secretary of State website. I made StateSmart to teach people the whole process. It covers: Understand the costs: Understanding all fees. Agent tips: Help with choosing a registered agent or becoming your own. Step-by-step instructions: Clear guidance on each document you need to file. Compliance: Tips on how to stay compliant with annual reports and filings. Everything online: All instructions and resources are available online. LegalZoom charged me hundreds for something you can do yourself. StateSmart helps you save money and stay in control. I built StateSmart using Next.js, Stripe, and Vercel. Thanks! Antonio https://bit.ly/3VdZfFm June 9, 2024 at 02:39AM

Show HN: I wrote a partial re-implementation of DirectMusic https://bit.ly/3Vc5IR7

Show HN: I wrote a partial re-implementation of DirectMusic DirectMusic[1] is a deprecated Windows API for playing dynamic music scores authored using DirectMusic Producer[2]. It was originally released as part of DirectX in 1999 and discontinued with the release in Windows Vista around 2009-ish. Due to my involvement with projects[3] re-implementing an old game engine for the early 2000's games Gothic and Gothic II[4], I came to notice that existing solutions[5] were incorrect and hard to use. Thus, I was tasked with writing a new, correct re-implementation of the API. Today, my re-implementation is able to (mostly) play back so-called style-based segments[6] and is fully tested against both the Gothic and Gothic II soundtracks. I am actively working on getting the Lego Island 2 soundtrack working as well. There are many features of DirectMusic which the library does not currently support, simply because I have not been able to find or test soundtracks using them, so if you want to contribute, I'd love to know about software shipping with DirectMusic soundtracks! [1]: https://bit.ly/3wYXRON [2]: https://bit.ly/3VhfKQR... [3]: Specifically GothicVR ( https://bit.ly/3XgdVGu ) and OpenGothic ( https://bit.ly/45fyxAx ) through my ZenKit library ( https://bit.ly/3VySq2o ) [4]: https://bit.ly/45f43Pc [5]: There is libdmusic ( https://bit.ly/45eIzSE ) which is unmaintained and an embedded implementation in OpenGothic ( https://bit.ly/45fyxAx ) [6]: https://bit.ly/45eReEq... https://bit.ly/3VzoxPq June 8, 2024 at 11:02AM

Show HN: I built job search platform for Architects https://bit.ly/3yPG7Wp

Show HN: I built job search platform for Architects Hi HN, I started my solopreneur journey this year and I’d like to share something I’ve been working on: ArchGee - a job search platform for architects, interior designers, urban planners, and other professionals in the architecture field. Coming from an IT background, I’ve seen plenty of job boards for IT roles. However, my architect friends often struggle to find job opportunities specific to their unique skills. Archgee is designed to fill this gap. It’s tailored exclusively for the architecture community, making it easier to find relevant opportunities. At first I am planning to integrate jobs from other search platforms (jobs that are relevant to architecture), then partnering with industry companies to ensure high-quality job posts and aim to create a supportive space for networking and growth. I’m here to seek your thoughts and feedback. Mirza June 8, 2024 at 08:10PM

Show HN: Speed up your Postgres queries by upto 90% https://bit.ly/3KyERcT

Show HN: Speed up your Postgres queries by upto 90% https://bit.ly/3V7Hwiw June 8, 2024 at 03:46PM

Show HN: MARS5, open-source, insanely prosodic TTS model https://bit.ly/4b9BmVr

Show HN: MARS5, open-source, insanely prosodic TTS model Hey guys, This is Akshat from CAMB.AI. Today's we're super pumped to introduce MARS5, a fully open-source (commercially usable) TTS with break-through prosody and realism available on our Github: https://bit.ly/3XeAmfb Watch our release demo here: https://www.youtube.com/watch?v=bmJSLPYrKtE Why is it different? MARS5 is able to replicate performances (from 2-3s of audio reference) in 140+ languages, even for extremely tough prosodic scenarios like sports commentary, movies, anime and more; hard prosody that most closed-source and open-source TTS models struggle with today. We're excited for you to try, build on and use MARS5 for research and creative applications. Let us know any feedback on our Discord: https://bit.ly/3xaMdAh https://bit.ly/3x6tXIq June 8, 2024 at 10:45AM

Show HN: PS2 Filter AI https://bit.ly/4eh370L

Show HN: PS2 Filter AI https://bit.ly/4aVFKXV June 8, 2024 at 01:10AM

Show HN: E-Paper 7-color display showing the current weather https://bit.ly/45cK2Zu

Show HN: E-Paper 7-color display showing the current weather A hobby project of mine that was surprisingly easy to put together! I love waking up and seeing the freshly generated image. https://bit.ly/4bOCfDT June 7, 2024 at 01:10PM

Show HN: I think I've built the most worthless SaaS on the internet https://bit.ly/45cJ1Ro

Show HN: I think I've built the most worthless SaaS on the internet https://bit.ly/45bfcRb June 7, 2024 at 08:07AM

Show HN: Archimede, the unobtrusive directory information fetcher https://bit.ly/3xhYF14

Show HN: Archimede, the unobtrusive directory information fetcher https://bit.ly/3VfTvuw June 6, 2024 at 10:10PM

Show HN: A Short IPv6 Guide for Home IPv4 Admins https://bit.ly/3xh5pMJ

Show HN: A Short IPv6 Guide for Home IPv4 Admins https://bit.ly/3yS4cw1 June 7, 2024 at 12:46AM

Show HN: Built an app that personalizes home workouts https://bit.ly/3VtKX4v

Show HN: Built an app that personalizes home workouts Hey HN, I’ve built and bootstrapped PARIAN. It designs personalized workouts so you reach your fitness goal quickly and efficiently. By training only with goal-specific exercises tailored to your experience level and preferred equipment (or just bodyweight), you skip the wasted time, effort, and disappointment. No more doom scrolling exercises, being overwhelmed by how to plan them, and being bombarded by noise from all the fitfluencers. You workout with confidence knowing each exercise is intentional and each session is moving you forward. Plus, you have the freedom to customize your program at any moment, ensuring the training is enjoyable - thus ensuring consistency. I believe fitness is not a lifestyle, but a core part of life and wanted to create something that will assist this pursuit of going after your fitness potential. And instill the excitement of all the new doors that will open up - bouldering, boxing, breakdancing, you name it. Being non technical I naturally leaned towards no-code platforms. Started building on Bubble in 2022 and launched the demo that December. I got some assistance from friends with html, css, and js along the way and officially launched the MVP in Feb 2023. The fitness app space is crowded, and ones that tailor workouts already exist—so why build this? Saturation is demand, and it’s easier to stand out in a crowd than to create your own market. When you break it down, most of the apps aren't personalized. Majority are workout trackers/loggers or just have a selection of pre-made workouts. The few apps that do personalize workouts create subpar programs with surface level tutorials and lack support, guidance, and customization. Additionally, even the most popular apps in this space have: — Questionable exercise selection — Exercise redundancy in the workouts — Excessive training volume — Require constant input throughout workouts The gap between 0 support and minimal structure (youtube/pdf plans), and hiring a personal trainer at a gym for hundreds of dollars is huge. While both have their time and place, I believe most would actually benefit working out with an app. Training from home, with bodyweight/available equipment is the fastest way to start that fitness journey - leveraging the device you spend the most time with. PARIAN is more than a workout tracker & planner - it’s a savvy training partner that guides you through personalized workouts and expedites your fitness journey. Just shipped an update, try a demo workout here — https://bit.ly/3yPq5vN Follow our journey — @parianlabs on insta Feedback and support is much appreciated! https://bit.ly/3yPq5Mj June 5, 2024 at 01:21AM

Show HN: Pipedream now has 2100+ API integrations https://bit.ly/3VqxwCt

Show HN: Pipedream now has 2100+ API integrations https://bit.ly/3TlTapk June 5, 2024 at 11:14PM

Show HN: EndType – Extract structured data from images, video and PDFs https://bit.ly/3yQJ8WD

Show HN: EndType – Extract structured data from images, video and PDFs https://bit.ly/3yYOHSI June 5, 2024 at 11:01AM

Show HN: Extract Data from Line Chart Image https://bit.ly/4emRyWb

Show HN: Extract Data from Line Chart Image Hey HN! Plextract extracts datapoints from a line chart image so you can compare and collect data from publications without manual effort! Enjoy and leave feedback. https://bit.ly/4ecsNLZ June 5, 2024 at 10:20AM

Show HN: zfind – CLI like find but using SQL syntax and also does tar/zip https://bit.ly/3Vslb0w

Show HN: zfind – CLI like find but using SQL syntax and also does tar/zip I wrote this because I needed to search a lot of files, including some archives, for files in a date range but couldn't find any good tools. Also I never liked find's option syntax. I think most people already know SQL (or at least it's easier to learn) and a much better match for this task. https://bit.ly/4bYqLNW June 5, 2024 at 09:19AM

Show HN: I created an German Demo Events App https://bit.ly/4c5cwa2

Show HN: I created an German Demo Events App I developed my first iOS App for sharing, finding and contributing to demos across Germany https://apple.co/4591QVy June 5, 2024 at 02:56AM

Show HN: AI Photography Platform, Make Better Option Than Traditional Photoshoot https://bit.ly/3Kvnp96

Show HN: AI Photography Platform, Make Better Option Than Traditional Photoshoot Hi HN, I develop AI photography platform designed to make photoshoots affordable, flexible, and faster compared to traditional methods. With POTO.AI, you can generate professional headshots, portraits, and couple wedding photos without the need for a physical photoshoot. All you need is one selfie, and POTO.AI will magically generate stunning photos for you. Let me know if you have any feedback and thank you for taking time to read this, grateful! https://bit.ly/4bKvJxZ June 4, 2024 at 04:26AM

Show HN: My side project isn't AI, crypto, or VR/AR. Looking for feedback:) https://bit.ly/4e4ozGn

Show HN: My side project isn't AI, crypto, or VR/AR. Looking for feedback:) I’m excited to share Savewise Cashback, a powerful new tool to help you save money on every online purchase. I was inspired to build this after I realized that cashback offers vary every day across every shopping portal. I imagined a “Google Flights” for cashback offers was something that would save me so much time, and help me earn more cash back and miles while shopping. With this tool, you no longer have to check every shopping portal to find the best cashback or mileage offers before making a purchase. It also shows you some historical data on offers by portal since the rates change every day, so you know whether or not you're getting a good deal on a given day. I hope you find this tool helpful - I’d love to hear your feedback and suggestions as I continue to improve this product. https://bit.ly/3Vbc17z June 4, 2024 at 01:45AM

Show HN: I created a reverse search engine to find the source of anime clips. https://bit.ly/4aN2adP

Show HN: I created a reverse search engine to find the source of anime clips. Hi, my name is Rayn. I am a solo independent entrepreneur. Initially, my only reason for learning was to make tons of money, but after completing the learning process, I was very confused about what my first project on the internet should be. I started browsing the internet for ideas but got bored and wasted time on social media. I noticed that in the comment sections of anime clips, many people were asking for the anime name and episode. That's when I thought, "Let's make an anime reverse search engine," and boom, Cleithral was born. Just upload a video, image, or gif, and it will give you the anime name and episode number. To be honest, I chose the name Cleithral because I had a failed Shopify shop with that domain name, so I just reused it. That's the story behind my first project. https://bit.ly/4aPzsJ4 June 4, 2024 at 01:19AM

Show HN: Australia focused tech job board https://bit.ly/4e368lp

Show HN: Australia focused tech job board https://bit.ly/4bIEW9M June 3, 2024 at 11:18AM

Show HN: Bliss – A constructed writing system for fast and beautiful writing https://bit.ly/3Kptkwm

Show HN: Bliss – A constructed writing system for fast and beautiful writing Of course, this is just for fun and is absolutely NOT to be used for anything related to security or secrecy. Anyway, I'd love to hear some feedback :) https://bit.ly/3Vq3VJy June 3, 2024 at 01:33AM

Show HN: Git-Backup – Back Up Your Git Repositories to S3 https://bit.ly/3yLvILD

Show HN: Git-Backup – Back Up Your Git Repositories to S3 https://bit.ly/3yLvJzb June 2, 2024 at 09:50PM

Show HN: Android Music Player That Can Download YouTube and Bilibili Music https://bit.ly/3WZzfQu

Show HN: Android Music Player That Can Download YouTube and Bilibili Music It's a music player designed for Android platform. However, you can build it for Linux that is my development environment. If you want to build a Macos, ios or Windows version, you can try it without guarantee it will work. It's based on Flutter and Rust. https://bit.ly/454pen9 June 2, 2024 at 03:32AM

Show HN: Fusio 5.0 released – open-source API management platform https://bit.ly/3XosZ59

Show HN: Fusio 5.0 released – open-source API management platform https://bit.ly/3j2iwGS June 2, 2024 at 09:47AM

Show HN: Open-Source Load Balancer for Llama.cpp https://bit.ly/3KpsBLF

Show HN: Open-Source Load Balancer for Llama.cpp Stateful load balancer customized for llama.cpp (with a reverse proxy). https://bit.ly/3wZYesa June 2, 2024 at 12:35AM

Show HN: What is my phone number https://bit.ly/4bIXsPr

Show HN: What is my phone number https://bit.ly/4aNiCe1 June 2, 2024 at 12:59AM