Show HN: HTML for People https://ift.tt/5RMq4UN

Show HN: HTML for People https://ift.tt/LEzTAHb October 10, 2024 at 11:17PM

Show HN: Arch – an intelligent prompt gateway built on Envoy https://ift.tt/zWGhCkm

Show HN: Arch – an intelligent prompt gateway built on Envoy Hi HN! My name is Adil Hafeez, and I am the Co-Founder at Katanemo and the lead developer behind Arch - an open source project for developers to build faster, generative AI apps. Previously I worked on Envoy at Lyft. Engineered with purpose-built LLMs, Arch handles the critical but undifferentiated tasks related to the handling and processing of prompts, including detecting and rejecting jailbreak attempts, intelligently calling “backend” APIs to fulfill the user’s request represented in a prompt, routing to and offering disaster recovery between upstream LLMs, and managing the observability of prompts and LLM interactions in a centralized way - all outside business logic. Here are some additional key details of the project, * Built on top of Envoy and is written in rust. It runs alongside application servers, and uses Envoy's proven HTTP management and scalability features to handle traffic related to prompts and LLMs. * Function calling for fast agentic and RAG apps. Engineered with purpose-built fast LLMs to handle fast, cost-effective, and accurate prompt-based tasks like function/API calling, and parameter extraction from prompts. * Prompt guardrails to prevent jailbreak attempts and ensure safe user interactions without writing a single line of code. * Manages LLM calls, offering smart retries, automatic cutover, and resilient upstream connections for continuous availability. * Uses the W3C Trace Context standard to enable complete request tracing across applications, ensuring compatibility with observability tools, and provides metrics to monitor latency, token usage, and error rates, helping optimize AI application performance. This is our first release, and would love to build alongside the community. We are just getting started on reinventing what we could do at the networking layer for prompts. Do check it out on GitHub at https://ift.tt/QGs5EIO . Please leave a comment or feedback here and I will be happy to answer. (I did make a mistake earlier not properly tagging the title with Show HN and the post didn't end up in Show HN. Later I updated the title but then my text started showing up as a comment. So I redid the post again, sorry if you had looked at the previous post already. Here is the link to the old post https://ift.tt/kJFHGnu ) https://ift.tt/gPrLMdW October 10, 2024 at 11:15PM

Show HN: AI detects resume "red flags" https://ift.tt/dHCOJIP

Show HN: AI detects resume "red flags" https://ift.tt/VQ3kIiN October 10, 2024 at 01:53AM

Show HN: VRE Dataset generation for MultiTask vision models training from videos https://ift.tt/6S8wZgq

Show HN: VRE Dataset generation for MultiTask vision models training from videos Been working on this tool for my PhD which involves training multi task vision models using various pre-trained models as inputs or pseudolabels in order to improve generalization. I work mostly on UAV datasets, but it should work okay on indoor scenes or self driving (at least Marigold and Mask2Former). For example, this dataset was generated using this tool: https://ift.tt/OLAv2p9 I'm quite aggressively trying to "just get the nn.Module" from the public repos that other researchers put up in their overly convoluted frameworks. A simple `forward(rgb_input: torch.Tensor) -> torch.Tensor` is nice, having 100 imports from a generic framework that has versions incompatibilities with everything else is not. PS: most mains are standalone runnable too, i.e. - https://ift.tt/OA7Xi8r... or - https://ift.tt/OA7Xi8r... https://ift.tt/aBRSjI3 October 9, 2024 at 11:09PM

Show HN: Parliament Wow makes sense of UK democracy https://ift.tt/o0nOtAm

Show HN: Parliament Wow makes sense of UK democracy Over the weekend we built Parliament Wow. It's hacky, buggy and slightly broken but it does the job :) Parliament Wow makes it easy to find out what is going on in parliament and what it actually means for you and me. We know that nobody has the time to watch hours of debates, drown in legal paperwork or keep up with the implications of every vote. Not me or you and least of all your MPs. There is just too much data. So we made a solution. We paired some semantic search with every publicly accessible document, audio recording or transcript we could get our hands on + some generative models to make it all look pretty. And we built a demo of what democracy could become. Parliament Wow won the a16z London Hackathon in the Build Back Britain category. Where should we go with this? https://ift.tt/fTrmDn4 October 9, 2024 at 12:39AM

Show HN: Actor Kit – XState Machines for Cloudflare Workers https://ift.tt/O8a9EJs

Show HN: Actor Kit – XState Machines for Cloudflare Workers Actor Kit is a library for running state machines in Cloudflare Workers, leveraging XState for robust state management. It provides a framework for managing the logic, lifecycle, persistence, synchronization, and access control of actors in a distributed environment. Key features include: - Persistent, distributed state management - Type-safe events and state with TypeScript and Zod - Real-time updates and seamless server-to-client state transfer - Access control and secure data management - Framework-agnostic with examples for Next.js and Remix integration - Actor lifecycle management in distributed environments - Support for real-time collaboration - State migration support The project is in early development, and I'm seeking feedback on the ideas and APIs. Cheers, Jon https://ift.tt/KkltpNd October 8, 2024 at 11:56PM

Show HN: I built this as a high school student to learn SQL with realistic data https://ift.tt/e7mwp94

Show HN: I built this as a high school student to learn SQL with realistic data https://sandboxsql.com October 8, 2024 at 12:07PM

Show HN: 2048-TUI – A cross platform terminal version of 2048 with sound support https://ift.tt/5fy6Y19

Show HN: 2048-TUI – A cross platform terminal version of 2048 with sound support https://ift.tt/KhTila2 October 8, 2024 at 05:02AM

Show HN: AI-generated images that look like real life https://ift.tt/eYpyXWL

Show HN: AI-generated images that look like real life https://ift.tt/I4w5nCY October 8, 2024 at 02:08AM

Show HN: Read Articles Without Ads https://ift.tt/JFMNBfV

Show HN: Read Articles Without Ads I've created an application that lets you read articles without ads + recommendation engine that picks 20 best articles for you to read everyday! https://ift.tt/YXN4GPK October 7, 2024 at 01:46AM

Show HN: Smart Account Starter - instant smart wallets/smart accounts https://ift.tt/zgR1mtj

Show HN: Smart Account Starter - instant smart wallets/smart accounts https://ift.tt/vtzY4qi October 7, 2024 at 01:49AM

Show HN: RemoteController – Steam Remote Play Alternative Powered by P2P and Web https://ift.tt/BeDovEQ

Show HN: RemoteController – Steam Remote Play Alternative Powered by P2P and Web https://ift.tt/HeuM4AJ October 7, 2024 at 12:18AM

Show HN:I made bot to help improve your mood using GPT o1-model https://ift.tt/Y89Ardz

Show HN:I made bot to help improve your mood using GPT o1-model https://ift.tt/p8THPJV October 6, 2024 at 10:56PM

Show HN: Production Quality AI True Crime Podcast Generator https://ift.tt/lsSQWK4

Show HN: Production Quality AI True Crime Podcast Generator Hello HN! My brother and I built Golpo, the first production-quality AI true crime podcast generator. Just tell Golpo what you want to listen to and it creates a real true crime podcast (usually > 30 min long) in minutes. Golpo does everything that a human podcastor would do. It first understands what you want to listen to, does highly detailed research on the case, creates a script and then uses that to create a production-quality podcast Golpo ensures that every story is meticulously fact-checked and based on real-life events. Say goodbye to waiting for new episodes and experience true crime made just for you on demand. Available today. No waitlist! Web: golpo.app App Store: https://ift.tt/80qefcZ... https://golpo.app October 6, 2024 at 02:30AM

Show HN: I turned my website into a Matrix-inspired 3D AI replica of me https://ift.tt/UX2eLqM

Show HN: I turned my website into a Matrix-inspired 3D AI replica of me https://ift.tt/Qk3YD57 October 5, 2024 at 11:18PM

Show HN: AzChat – Chat with Azure OpenAI Service https://ift.tt/QELg2wF

Show HN: AzChat – Chat with Azure OpenAI Service https://ift.tt/6nuszCV October 5, 2024 at 09:15PM

Show HN: TailwindCSS-motion / a simple syntax to animate in Tailwind CSS https://ift.tt/UFMjkKE

Show HN: TailwindCSS-motion / a simple syntax to animate in Tailwind CSS A plugin designed to make adding animations to your projects effortless We’ve made the API intuitive. Want a slide and fade effect? Just use motion-translate-x-in-25 motion-opacity-in-0. Or, opt for a preset like motion-preset-fade for quick implementation. https://ift.tt/saVJHft October 5, 2024 at 01:03AM

Show HN: The Gmail unsubscribe tool with bulk deletion and personal data removal https://ift.tt/OnUNDar

Show HN: The Gmail unsubscribe tool with bulk deletion and personal data removal https://againstdata.com October 5, 2024 at 12:55AM

Show HN: open source framework OpenAI uses for Advanced Voice https://ift.tt/k9mtEDL

Show HN: open source framework OpenAI uses for Advanced Voice Hey HN, we've been working with OpenAI for the past few months on the new Realtime API. The goal is to give everyone access to the same stack that underpins Advanced Voice in the ChatGPT app. Under the hood it works like this: - A user's speech is captured by a LiveKit client SDK in the ChatGPT app - Their speech is streamed using WebRTC to OpenAI’s voice agent - The agent relays the speech prompt over websocket to GPT-4o - GPT-4o runs inference and streams speech packets (over websocket) back to the agent - The agent relays generated speech using WebRTC back to the user’s device The Realtime API that OpenAI launched is the websocket interface to GPT-4o. This backend framework covers the voice agent portion. Besides having additional logic like function calling, the agent fundamentally proxies WebRTC to websocket. The reason for this is because websocket isn’t the best choice for client-server communication. The vast majority of packet loss occurs between a server and client device and websocket doesn’t provide programmatic control or intervention in lossy network environments like WiFi or cellular. Packet loss leads to higher latency and choppy or garbled audio. https://ift.tt/ymOT3Hz October 4, 2024 at 10:31PM

Show HN: I made a super-simple image CDN https://ift.tt/Rd2Uh6r

Show HN: I made a super-simple image CDN Hi HN, MageCDN is a simple and affordable image hosting service I have been working on for the past few weeks. The idea came out of my own frustration with hosting and optimizing images for my blog. While platforms like Imgur make it really simple to upload images, they don't allow you to embed them. Services like Cloudinary, Imagekit exist, but I found them too complex for my needs. Plus, they get really expensive past their free tier. So, I started MageCDN with three simple goals: - pricing should be affordable and scale linearly. - basic image operations (resize, crop, optimize) should be doable within the app. - uploading and getting a link you can use should be fast and hassle-free. Would love to hear what you think! https://magecdn.com/ October 3, 2024 at 09:04PM