Show HN: Attempt to bring a cinematic experience in 256 bytes (WASM) https://ift.tt/5t37yor

Show HN: Attempt to bring a cinematic experience in 256 bytes (WASM) https://ift.tt/4eAfCHW May 12, 2024 at 02:18AM

Show HN: A graph based arbitrage calculator https://ift.tt/l1XVoaQ

Show HN: A graph based arbitrage calculator It works by finding negative cycles in a graph https://ift.tt/WXTtcr6 May 12, 2024 at 03:42AM

Show HN: Project Random – Random, obscure content from around the web https://ift.tt/lAuacON

Show HN: Project Random – Random, obscure content from around the web https://ift.tt/dzRN7FV May 11, 2024 at 11:58PM

Show HN: Building a Jarvis-Like AI Program with ZeroLM and ChatGPT https://ift.tt/NiG2Kbz

Show HN: Building a Jarvis-Like AI Program with ZeroLM and ChatGPT https://ift.tt/BYz2am9 May 11, 2024 at 02:23PM

Show HN: MinimalChat – A Simple and Customizable LLM Chat Application https://ift.tt/hts5nXD

Show HN: MinimalChat – A Simple and Customizable LLM Chat Application Hello everyone! I have a hobby project that has become fairly full featured that I figured I would share. The idea of MinimalChat has been to create a project that is a lightweight and dead simple application that can be deployed locally in a few seconds (with docker). While of course also having most of the nice to have features and looking pretty nice. A nice bonus is it a Progressive Web Application so it can be installed like a normal application to your mobile device. It has a full mobile UI. For those using Chrome and Edge you can also locally download, load and host entirely via your browser models like LLama-3-8b with hardware acceleration via WebGPU. It's pretty experimental but it does work! I won't bloat this post reiterating it's features, the GitHub Readme gives a good idea of the application abilities. I know chat applications are a dime a dozen but...here's another one hah! https://ift.tt/WRqPbJ0 May 11, 2024 at 09:19AM

Show HN: Jacinda, a functional Awk (text stream processing on the comamnd-line) https://ift.tt/ZPiuwB7

Show HN: Jacinda, a functional Awk (text stream processing on the comamnd-line) Typed, functional (folds, scans) stream processing backed by Andrew Gallant/burntsushi's regular expressions library. There's a guide here! https://ift.tt/GQ3ry0e https://ift.tt/Eo8Igd9 May 10, 2024 at 10:39PM

Show HN: AI Runner – my personal opensource, local, multi-modal, AI assistant https://ift.tt/92lMLX8

Show HN: AI Runner – my personal opensource, local, multi-modal, AI assistant AI Runner is an application I have been working on for well over a year. I am the only developer on the project. I currently do not have a job so I have treated this as my full-time job. 3.0 is not yet ready for release, but I wanted to show you some of the cool things I've done with it (see video in link or check out my youtube page for past progress updates https://www.youtube.com/@capsizegames4331 ). AI Runner is a privacy-forward, multi-modal offline AI application built with Pyside6, huggingface libraries, llamaindex and open source models. It allows for real-time text to speech conversations with chatbot agents that you can fully customize. The bots have personalities and "moods". The moods shift with the conversation. I am using custom agents and my own system for selecting actions which is very fast. The application also allows you to generate images using Stable Diffusion and controlnet (previous versions allowed Kandinsky), LLM for chatbots and RAG retrieval using Mistral 7b and T5, multi-lingual text-to-speech using speech-t5, bark and espeak. The whole thing can run on a single 2080s video card, or you can split it between multiple GPUs by assigning models to available cards. For example, I have a 2080s which I use for Stable Diffusion, and a 3060 that I use for the other models. I've built in lots of features such as drawing tools, RAG for documents and websites, image generation with the LLM or custom prompts and more. I post about it often on my Twitter acount ( https://twitter.com/xw4ffl35x ). In addition to being a stand-alone application, the goal is to make it usable as an engine to power other applications. For example I plan to use it to power an RPG I am developing in Pygame. The application is pure python and can be compiled with pyinstaller using the installation scripts included in the main repo ( https://ift.tt/31LQqYN ). I am currently working on v3.0.0 which is under heavy development and is not stable. The last stable version came out over 8 months ago and was version 2.2 (you can find it tagged on github). This new version is a complete refactor and uses proper threading, has enhanced privacy and security features (the app is not able to access the internet and complete works around any security holes in the huggingface libraries by preventing them from accessing the internet or creating a .cache folder - there's more information about this in the README). --- I believe it is crucially important to have open source options when it comes to AI. I do not want to live in a world that is dominated by OpenAI. I want free, open source models and the ability to run them locally, offline for free. If you would like to support my efforts, please consider donating via patreon https://ift.tt/IL5iQZ0 https://twitter.com/xw4ffl35x/status/1778094355812700635 May 11, 2024 at 02:12AM

Show HN: A web debugger an ex-Cloudflare team has been working on for 4 years https://ift.tt/yB3CQqi

Show HN: A web debugger an ex-Cloudflare team has been working on for 4 years Hey HN, I wanted to show you a product a small team and I have been working on for 4 years. https://jam.dev It’s called Jam and it prevents product managers (like I used to be) from being able to create vague and un-reproducible bug tickets (like I used to create). It’s actually really hard as a non-engineer to file useful bug tickets for engineers. Like, sometimes I thought I included a screenshot, but the important information the engineer needed was what was actually right outside the boundary of the screenshot I took. Or I'd write that something "didn't work" but the engineer wasn't sure if I meant that it returned an error or if it was unresponsive. So the engineer would be frustrated, I would be frustrated, and fixing stuff would slow to a halt while we went back and forth to clarify how to repro the issue over async Jira comments. It’s actually pretty crazy that while so much has changed in how we develop software (heck, we have types in javascript now*), the way we capture and report bugs is just as manual and lossy as it was in the 1990’s. We can run assembly in the browser but there’s still no tooling to help a non-engineer show a bug to an engineer productively. So that’s what Jam is. Dev tools + video in a link. It’s like a shareable HAR file synced to a video recording of the session. And besides video, you can use it to share an instant replay of a bug that just happened — basically a 30 second playback of the DOM as a video. We’ve spent a lot of time adding in a ton of niceties, like Jam writes automatic repro steps for you, and Jam’s dev tools use the same keyboard shortcuts you’re used to in Chrome dev tools, and our team’s personal favorite: Jam parses GraphQL responses and pulls out mutation names and errors (which is important because GraphQL uses one endpoint for all requests and always returns a 200, meaning you usually have to sift through every GraphQL request when debugging to find the one you’re looking for) We’re now 2 years in to the product being live and people have used Jam to fix more than 2 million bugs - which makes me so happy - but there’s still a ton to do. I wanted to open up for discussion here and get your feedback and opinions how can we make it even more valuable for you debugging? The worst part of the engineering job is debugging and not even being able to repro the issue, it’s not even really engineering, it’s just a communication gap, one that we should be able to solve with tools. So yeah excited to get your feedback and hear your thoughts how we can make debugging just a little less frustrating. (Jam is free to use forever — there is a paid tier for features real companies would need, but we’re keeping a large free plan forever. We learned to build products at Cloudflare and free tier is in our ethos, both my co-founder and I and about half the team is ex-Cloudflare) and what we loved there is how much great feedback we’d get because the product was mostly free to use. We definitely want to keep that going at Jam.) By the way, we’re hiring engineers and if this is a problem that excites you, we’d love to chat: jam.dev/careers May 10, 2024 at 06:38PM

Show HN: MamaRap – AI-Generated Personalized Music Videos for Mothers https://ift.tt/ylzW4c7

Show HN: MamaRap – AI-Generated Personalized Music Videos for Mothers Hello HN, I'm excited to share a project we launched - MamaRAP. What It Does: MamaRap generates personalized rap songs for mothers based on user inputs on the mother's treats and memories. The tool composes the lyrics, the accompanying music, and a one-minute video clip. Try It Out: We'd love your feedback. Use the promo code HN50OFF to get a 50% discount on generating the song. No sign-ups required. Looking forward to your feedback. We value your thoughts and input on our product and idea. https://ift.tt/pwZaH8n May 10, 2024 at 01:15PM

Show HN: I Made an AI Social Media Manager to Automate Content Creation https://ift.tt/IkyLt0T

Show HN: I Made an AI Social Media Manager to Automate Content Creation Hey HN, I am a Solopreneur, and I love building apps to automate boring tasks. Over the years, I happened to have launched a couple of products, blogs, and small businesses, and managing their social media pages has always been stressful. For some time, I hired a VA to manage some of these pages, later I moved to creating content and scheduling it for my social media pages but then I got tired. But with the recent advancements in AI, I decided to build AI Engager, an AI-powered Social Media Manager that creates and posts content with images on all your projects/business Facebook pages and Twitter accounts. No more worrying about keeping my project's social media pages alive, AI Engager handles it and it can handle it for you too. I hope this tool will be as helpful to you as it is to me. I would love your feedback pls. https://ift.tt/fBcDhHo May 10, 2024 at 02:12PM

Show HN: Loglayer: A fluid logging interface for JavaScript loggers https://ift.tt/z6ye30h

Show HN: Loglayer: A fluid logging interface for JavaScript loggers This has been in use on our production systems for around two years now at Switchboard ( https://switchboard.app ). The problem we had was that we were using two different logging libs for our frontend and backend at the time (specifically roarr, and bunyan), and the API for the logging libs were not compatible with each other. Loglayer was designed to wrap around popular JS logging libraries where you can swap out any underlying library without re-writing your log entries to adapt to the new library. One common example is using plain "console" as a starting integration, but later swapping to a logging library like Winston once you've nailed down which JS logging lib fits your use-case. You can also swap to another from there (which we have done from bunyan to pino on our backend) if you need to later on. It also provides a fluid API that standardizes how one should feed error, set context, and metadata. This means regardless of the underlying logging library used, developers use the same API to write logs throughout. log .withMetadata({ some: 'data'}) .withError(new Error('test')) .info('my message') With this new 4.x release, I added a plugin system allowing you to manipulate data before it is shipped to the underlying JS logger). https://ift.tt/KuCvhl2 May 10, 2024 at 12:15AM

Show HN: I created 3,800+ Open Source React Icons (Beautiful, Rounded Style) https://ift.tt/Oa0JSGq

Show HN: I created 3,800+ Open Source React Icons (Beautiful, Rounded Style) I’ve created a library of beautiful rounded icons and would like to share it with the Hacker News community. Any suggestions are highly appreciated. Features: - Beautifully rounded style - Over 3,800 icons - Editable stroke - Regularly adding new icons - Another standard version (less rounded) coming soon - Easy installation via npm or yarn https://ift.tt/ITXMqGW May 8, 2024 at 11:47PM

Show HN: A multi-modal and AI first Knowledge Management System https://ift.tt/xliB5oK

Show HN: A multi-modal and AI first Knowledge Management System User Very much a work in progress, but building a LLM first PKMS (Personal Knowledge Management System). Here's what it allows you to do: - Express yourself in the way you want: supports text, whiteboards, OCR, audio and videos. Just dump info in the way you want. - Comprehension and brainstorming: convert say whiteboard scribble to a diagram or text to chart. - Notebook to interactive mindmaps using AI. You can also chat against the mindmap - Export your notebook as content. Be it a blogpost or a newsletter or whatever. - Chat support with references back to your notes across your whole knowledgebase. Look forward to hearing feedback. It's very early and I am a solo dev doing this part-time. https://ift.tt/0gKDMWd May 9, 2024 at 02:18AM

Show HN: Explore Tor relays on a world map over time https://ift.tt/fl3sFnJ

Show HN: Explore Tor relays on a world map over time Hey HN, Together with a friend from university, I build a world map to show the distribution of public Tor relays. The historical state of the network can be viewed for any day between October 2007 and today: https://tormap.org/ We look up the current geolocation of IP addresses collected from the official Tor project archives: https://ift.tt/RJm4jBl Over time, the project has grown to support more features such as extensive filtering, searching, visualisation of different groupings, and looking up details of individual relays. Source code for both the frontend and backend is also available here: https://ift.tt/SXnxD03 We hope you find our little web app useful and would love to hear your feedback. Cheers, Julius https://tormap.org May 9, 2024 at 01:42AM

Show HN: An AI logo generator that can also generate SVG logos https://ift.tt/iJ8jvsS

Show HN: An AI logo generator that can also generate SVG logos Hey everyone, I've spent the past 2 weeks building an AI logo generator, which can also generate high-quality SVG logos (bw/silhouette only for now). You can choose a style from a gallery of options and adjust the prompt/keywords however you like. The rest is pretty self-explanatory. https://createlogo.app/ May 9, 2024 at 12:00AM

Show HN: I made a calculator builder to increase engagement and conversions https://ift.tt/OGaC3wX

Show HN: I made a calculator builder to increase engagement and conversions Hi HN, I am a solopreneur in the evenings and a software engineer during the day. In the past, I have created lots of calculators for my web projects and freelancing friends. These were pretty basic, but users always welcomed them. I also used currently available builders, but the problem was that they were either slow, broke on mobile devices, had nonsense page view limits, or were expensive. Some even ticked all those boxes. So I have decided to create my own, with a simple interface, and called it Creative Widgets (if it ever takes off, I plan to add more exciting stuff like charts, etc, hence why generic “Widgets”). At this point, I am after feedback. I found myself running in a circle, building features because I think they're great to have, but I would much rather have features that are wanted by users. So, if your project/web benefits from the custom calculator, you can check it out. Thanks everyone. Eugen https://ift.tt/fVux2e1 May 8, 2024 at 02:24AM

Show HN: Skyrim – Open-source Large Weather Model (LWM) Zoo https://ift.tt/sjGmhRp

Show HN: Skyrim – Open-source Large Weather Model (LWM) Zoo Hi HN, I'm Efe from Secondlaw AI. We are building physics-informed large AI models. Currently, we are focusing on weather modelling. To benchmark SOTA, we had to build a forecasting infra for all available large weather models and we could not find a solid tooling to do so, so we built Skyrim. Within <5 mins and <5 LOC you can run forecasts on par with global weather models that are run on 100K+ CPU HPCs! We are implementing more models & fine-tuning capabilities. Let us know if anything more we can add, also happy to answer any questions! https://github.com/secondlaw-ai/skyrim May 7, 2024 at 09:33PM

Show HN: Voltage Park – H100 GPU Orderbook https://ift.tt/LB8mtHW

Show HN: Voltage Park – H100 GPU Orderbook Hi HN - Voltage Park is a GPU cloud powered by Nvidia H100s. We own and manage the infrastructure and currently have over 7,000 H100s live. We will be launching an additional 17,000 H100s in the next 2 months. Today, we are launching our H100 Auction Platform with 1,000+ GPUs live. This platform gives users on-demand access to compute for AI training, fine-tuning, and inference. We are growing the platform to over 5,000 H100s in the next month. We created the Auction Platform to make the process of procuring GPUs more transparent and simple. It allows you to see the supply and price of GPUs in real-time. Place an order for the number of GPUs you need and get near-instant access to the compute. We have been running this on-demand auction platform for the past 2 months in Beta. Early customers include Luma AI, 273 Ventures and Mirelo.ai. One great customer comment so far: “I love using Voltage Park auction. It's so empowering to know we can spin up high-perf GPU nodes if we need them at affordable prices." -- Carl Johann SIMON (CEO, mirelo.ai) We will be hosting a Zoom on Thursday, May 9th at 12pm PT to go over the platform in more detail and answer any questions you may have. Please email ozan [at] voltagepark [dot] com if you would like to attend. We love the curiosity and spirit of the HN community, so please let us know what feedback you have. Our goal is to make machine learning accessible to all and this is just the start! Voltage Park Auction Platform Infrastructure: - Infrastructure - Owned by Voltage Park (we are not a reseller) - Hardware - 8x 80GB H100 SXM5 | 1.0 Tb DDR5 RAM with ECC | 2x 52-core CPUs | 100Gbps Ethernet - Minimum Order - 8 GPUs - Data Center Locations - Texas, Virgina, and Washington https://ift.tt/j8dPUEA May 7, 2024 at 11:36PM

Show HN: Live Storm Chasing https://ift.tt/D3qXKuM

Show HN: Live Storm Chasing https://www.youtube.com/watch?v=JBw3XJc7jRc May 7, 2024 at 06:31AM

Show HN: I built a Notion for science https://ift.tt/psKtXhy

Show HN: I built a Notion for science I struggle with handwritten notes, but it's always been the primary way to write scientific notes. To do scientific writing on existing keyboard-and-mouse tools generally requires either significant knowledge of the software, the use of screenshotting/exporting from external tools, or (often) both. That's why I made Stempad, which is meant to rival the speed of pen-and-paper for scientific writing. I've currently added 7 different scientific blocks (and several basic blocks too) and plan to continuously add more. Questions are welcome, and preliminary feedback or constructive criticism is really appreciated! (If you're on mobile or would prefer to see a demo, here is one: https://www.youtube.com/watch?v=U-9j8sFIkS4 ) https://www.stempad.io May 7, 2024 at 04:11AM