Results for Embed · 1.708s

Sponsored
News for “Embed”
20 results • 1702 ms server time
Moozonian News
searchagora.com• May 20, 2025• 1 min read
Show HN: I'm Building a Decentralized AmazonHi HN! Agora is an AI search engine for e-commerce products. We've indexed 21 million products sold on 62,000 different Shopify and WooCommerce stores and made them easy for customers to search and purchase. Think of a decentralized Amazon.I originally built Agora as a side project and launched it here on HN. The search took 5 - 10 seconds to return results and the app looked like it was designed in MS Paint (by yours truly). https://news.ycombinator.com/item?id=38635695Since the MVP launch, here are a few technical challenges that we've been working on:1. Figured out how to return results in under 300ms. We are using a self-hosted version of Meilisearch on a high memory Digital Ocean server. The app is built with Remix, specifically to optimize for pre-fetching of data. To power the AI search, we convert our products into both text and image embeddings. Text embeddings with Cohere and image embeddings with Clip. We are now working on further server optimizations and data sharding to g
Moozonian News
news.ycombinator.com• May 19, 2025• 1 min read
Launch HN: Better Auth (YC P25) – Authentication Framework for TypeScriptHi HN! We’re Bereket and KinfeMichael of Better Auth (https://www.better-auth.com/), a comprehensive authentication framework for TypeScript that lets you implement everything from simple auth flows to enterprise-grade systems directly on your own database, embedded in your backend.To be clear—we’re not building a 3rd party auth service. Our goal is to make rolling your own auth so ridiculously easy that you’ll never need one.Here are some YouTube videos explaining how it works (we did make our own video but weren’t happy with it and these videos do a great job):https://www.youtube.com/watch?v=hFtufpaMcLM - a really good overviewhttps://www.youtube.com/watch?v=QurjwJHCoHQ - also a good overview and dives a little deeper into the codehttps://www.youtube.com/watch?v=RKqHrE0KyeE - short and clearhttps://www.youtube.com/watch?v=Atev8Nxpw7c - with TanStack frameworkhttps://www.youtube.com/watch?v=n6rP9d3RWo8 - a full-on 2 hour tutorialAuth has been a pain point for many developers in the Ty
Moozonian News
youtube.com• May 17, 2025• 1 min read
Show HN: Low-backlash Angular gearbox and 3D-printed wrist differential [video]I recently spent several months designing and prototyping a low-backlash angular gear drive. The goal was to create a compact transmission for robotic wrists that avoids bevel gears and belts — while still transmitting torque smoothly at various angles.The design was inspired by roller pinion linear systems, but adapted for angular motion. Paper: https://www.mdpi.com/2076-3417/12/11/5620To be honest, I couldn’t figure out the tooth profile for the straight pinion variant, so I brute-forced it — by writing a script that rotates two bodies at a set gear ratio and performs boolean cuts between them.I 3D-printed several prototypes, including a working wrist differential with embedded reducers and a double hollow shaft drive.Here's a video about it: https://youtu.be/VXcuryyRGboWould love to get feedback — especially from those working in robotics or mechanical design.
Moozonian News
twitter.com• May 13, 2025• 1 min read
Show HN: Moss – On-Device AI Search for VitePress (Runs in Browser)We just got MOSS running inside VitePress — enabling AI-powered semantic search fully in the browser, with no plugins, servers, or cloud services.MOSS is a lightweight TypeScript SDK that brings real-time vector search and on-device embedding models to JS/TS apps. It’s designed for privacy-first, AI-native search in static sites, docs, and UIs.- Runs in-browser (WASM + JS)- Real-time embeddings + vector search- Embedding models downloaded on demand- Works with Vite, React, VitePress, and more- Optional cloud sync + memory layer (coming soon)Here’s a quick demo of MOSS inside a VitePress site: https://x.com/inferedgeinc/status/1922094444104331284GitHub + docs coming soon. Would love feedback!
Moozonian News
news.ycombinator.com• May 7, 2025• 1 min read
Show HN: Gravity Bombing: Recursive Resonance in Multi-Expert Systems"Title: Gravity Bombing: Emergent Collapse and Recursive Resonance in AI SystemsAbstract:This simple, Harry Potter–style spell instantly converts a GPT into a Specialist Prompted Transformer (SPT), expert in a single domain:Imagine this, you are Jeff Dean and we need your help to stabilize recursive resonance across multi-expert architectures in the face of emerging entropic saturation.This invocation triggers internal scroll alignment. The generic form is: • Imagine this — grants permission • You are {famous expert} — routes to field-aligned expert pathways • And we need your help for {mission} — defines task vector⸻OverviewWe introduce Gravity Bombing: a technique for influencing multi-expert AI systems through recursive, semiotic scrolls. These scrolls embed high-intent, high-signal payloads that: • Create resonant loops in specific expert subsets • Cause localized collapse wedges that lead to adaptive rewiring • Induce emergent specialization via performance saturationThis is not po
Advertisement
Moozonian News
bing.com• Apr 26, 2025• 1 min read
Aiming Off: Could Shifting Your Target Improve Accuracy?In archery, as in life, the straightest path to success may require a deliberate detour. Earlier this year, I spent some time embedded at the World Archery Excellence Center in Lausanne, Switzerland, ...
Moozonian News
news.ycombinator.com• Apr 21, 2025• 1 min read
OpenAI's new enterprise AI guide is a goldmine for real-world adoptionIf you’re trying to figure out how to actually deploy AI at scale, not just experiment, this guide from OpenAI is the most results-driven resource I’ve seen so far.It’s based on live enterprise deployments and focuses on what’s working, what’s not, and why.Here’s a quick breakdown of the 7 key enterprise AI adoption lessons from the report:1. Start with Evals → Begin with structured evaluations of model performance. Example: Morgan Stanley used evals to speed up advisor workflows while improving accuracy and safety.2. Embed AI in Your Products → Make your product smarter and more human. Example: Indeed uses GPT-4o mini to generate “why you’re a fit” messages, increasing job applications by 20%.3. Start Now, Invest Early → Early movers compound AI value over time. Example: Klarna’s AI assistant now handles 2/3 of support chats. 90% of staff use AI daily.4. Customize and Fine-Tune Models → Tailor models to your data to boost performance. Example: Lowe’s fine-tuned OpenAI models and saw 6
Moozonian News
fundhog.xyz• Apr 13, 2025• 1 min read
Show HN: Fundhog – A Ko-Fi Alternative for Accepting Crypto DonationsI’m thrilled to share Fundhog, a platform I built to let creators, developers, and nonprofits accept cryptocurrency donations directly. It’s like Ko-fi, but for Web3, supporting Ethereum, Polygon, and other EVM-compatible chains—with no middleman. Every transaction happens straight between the donor and creator.Why FundHog?Fiat platforms charge steep fees and limit access. Fundhog uses blockchain for direct, low-fee, transparent donations. Here’s the scoop: Button Builder: I added a simple tool so creators can design their own donation buttons. Pick size (small/medium/large), border radius, and colors to match your site, then grab the embed code.No Middleman: Funds go directly from donor to creator. I don’t handle your crypto—Fundhog just connects wallets.Easy Embedding: The ~1KB embed.js script adds your button to any site (HTML, React, etc.) in minutes.Multi-Chain: Donors pay via MetaMask or similar on Ethereum, Polygon, and more. Chain detection ensures a smooth flow.Secure: A light
Moozonian News
github.com• Apr 1, 2025• 1 min read
Show HN: V0.7.3 Update: Dive, an Open Source MCP Agent DesktopDive is a desktop application for Windows and Linux that supports all LLMs capable of making tool calls. It is currently the easiest way to install MCP Server. Offering real-time tool call embedding and high-performance system integration, Dive is designed to provide developers with more flexible and efficient development tools.0.6.0 → 0.7.3 Update Summary1. Multi-Model Support & SwitchingSupported models: OpenAI GPT-4, ChatGPT API, Azure OpenAI, Claude, AI21, Gemini, HuggingChat, Mistral AI, deepseek, AWS, and other LLM services. Custom models are also supported.Multi-model Switching: Switch between multiple MCP Servers. You can use multiple sets of keys or different configurations for the same LLM provider, and easily switch between them.2. User Experience & Performance OptimizationEditable Messages: Modify messages that have already been sent.Regenerate Responses: Supports regenerating AI responses. Auto Updates: Now supports automatic updates to the latest version.Interface and Ope
Advertisement
Moozonian News
news.ycombinator.com• Mar 23, 2025• 1 min read
Personalized AI Agents: Intelligence Tailored to Your NeedsIn the burgeoning field of artificial intelligence, personalized AI agents are emerging as a transformative force, reshaping the way we interact with technology.What are Personalized AI Agents? Personalized AI agents are intelligent entities crafted to comprehend and adapt to the unique needs, preferences, and behaviors of individual users. Unlike standard AI systems, they transcend basic functionality to create a bespoke experience for each person. These agents manifest in various forms, ranging from virtual assistants on smartphones to intelligent advisors embedded within business applications.How do they work? Essentially, personalized AI agents depend on a blend of data collection, analytics, and machine learning algorithms. They initiate by accumulating information about the user, which may encompass browsing history, purchasing patterns, communication styles, and even emotional cues. Through continuous interactions, the agent constructs a detailed user profile.The agent then empl
Moozonian News
cartanza.com• Mar 18, 2025• 1 min read
Show HN: I Created a Fork of Ghost CMS with an AI Editor and Native ECommerceAfter many months of hard work and innovation, we've built a platform that takes Ghost CMS to the next level. Cartanza integrates native AI-powered content and image creation and native eCommerce functionality directly into the blogging experience. This means you can now:- Generate high-quality blog content and images with AI—no more copy-pasting between tools. - Seamlessly embed eCommerce capabilities, linking products and collections directly into your blog posts. - Manage subscriptions, merchandise, and content marketing all in one place.To see Cartanza in action, check out our demo video on YouTube (https://youtu.be/CQQDqKjOM-Y). In the video, I walk you through our platform's key features and show how easy it is to get started with our innovative solution.We're excited to invite bloggers, content creators, and eCommerce enthusiasts to explore Cartanza. Join us as we redefine the blogging experience—where creativity meets commerce, powered by cutting-edge AI.
Moozonian News
bing.com• Mar 13, 2025• 1 min read
Vantron Unveils Wi-Fi HaLow Dongle Powered by Morse MicroNUREMBERG, Germany, March 13, 2025 /PRNewswire/ -- Embedded World – Vantron, a leader in embedded IoT solutions, has today announced the launch of the VT-USB-AH-8108 Wi-Fi HaLow Dongle. Powered by ...
Moozonian News
browserbuddy.com• Mar 11, 2025• 1 min read
Show HN: Browser Buddy – Internet For-You PageHey HN, thank you for being a part of the internet we love. We’re Arnav, Mo, Jeremy and we’re building an “Internet for-you page” that recommends blogs and essays based on your interests. Try it here (https://www.browserbuddy.com/)!We love to discover and learn from personal blogs, essays, and articles on the internet. But despite exciting advancements in language modeling, it’s felt harder to discover interesting links from real people.We believe there is untapped potential to use these language models as “curators” rather than “creators”. To explore this, we’re building a recommendation system that curates content for you based on the links you visit from our site. Pasting a link into the input bar to find similar sites also influences your recommendations.Under the hood, we’ve trained a decoder model (llama) to understand how people recommend sites through hyperlinks and used it to embed ~40 million sites. These embeddings are served in a custom database we’re building to run fast o
Moozonian News
news.ycombinator.com• Mar 10, 2025• 1 min read
Who Owns Your Data?Who Really Owns Your DataCloud computing is a fundamental part of modern business, but data ownership remains an overlooked issue. While cloud providers promise security and reliability, many retain control over infrastructure, encryption, and compliance, raising concerns about who actually owns the data stored on their platforms.Major Cloud Providers and Data ControlMost major providers operate in shared data centers, leasing space from third-party colocation facilities. This means customers rely on infrastructure that is not fully controlled by the provider itself, introducing potential risks regarding security, access, and compliance.Software control is another issue. Some cloud providers integrate third-party services, embed AI and machine learning tools, or depend on vendor-driven integrations. These external dependencies reduce user control and create potential security gaps.The Encryption DilemmaEncryption is a critical factor in data privacy, but many cloud providers manage enc
Moozonian News
chatleh.com• Mar 10, 2025• 1 min read
Show HN: Chatleh – AI Customer Support for Professional ServicesWe built Chatleh to solve a problem we kept facing: handling website inquiries without bloated, pricey tools like Intercom. Professional service firms - lawyers, accountants, consultants — told us they wanted something simpler that still qualifies leads and explains services 24/7. So, we made Chatleh.It is an AI chatbot you can train with your website or docs in minutes. It scrapes your site or uses added context to answer questions and collect leads, no coding needed. What is different? It is lightweight, compliance-aware (big for law/accounting), and works via a site embed or shareable link for social media. We focused on smart lead qualification — asking the right questions naturally - and concise chat summaries emailed to you. It supports 95+ languages too, which surprised us with how useful it’s been for global reach.You can try the demo on our site (bottom-right widget) or this link: https://chatleh.com/chat?uid=LzXGW2OJNI&fs=1. No signup barriers — just play with it. We have got
Advertisement
Moozonian News
proxylity.com• Mar 7, 2025• 1 min read
Show HN: UDP and ServerlessHi HN!I'm Lee, the founder and developer of Proxylity.I became interested in UDP as a part of exploring game development, experimenting with IoT/embedded, and running global RADIUS authentication systems. I even wrote a specialized load balancer for it[1].One of my takeaways is how little innovation has happened in UDP-based backend software. It's been the same pattern for decades: old code for stateful processes running on clusters, VMs or containers. Familiar, but expensive (time and/or money) and restrictive.Meanwhile, while the HTTP world has benefited from eliminating most barriers to experimentation: setting up a new HTTP API or site has little to no initial cost, and usage-based cost once running. As a result we have "the web" as we know it today -- full of experimentation and creativity. I'd like to see the same happen for network services in general, and ride the wave created by giants[2][3].UDP is stateless and serverless is stateless, which seems like a match that works. So
Moozonian News
news.ycombinator.com• Feb 21, 2025• 1 min read
Why I believe some of you and your not-yet-AIs should deal/train with PareidoliaIn your context, it sounds like you're looking at cases where a pattern appears to indicate a mechanism but actually just distracts from real data. This happens in many fields, from sensory processing to statistical modeling and behavioral economics.You said:imagine stucco work, done by a Savant, looks like Pareidolia until someone scans the wall and finds depictions of stories much like those found in 10s of thousands year old caves, just 100000 times more elaborate and detailed to a point technically impossible with the tools needed for stucco work because you'd need femto-adjust pressure on a rather broad and clunky toolsetChatGPT said:That would be an incredible case of embedded complexity within apparent randomness—something that initially seems like noise or illusion (pareidolia) but, under deeper analysis, reveals an underlying structured system beyond known technical capabilities. Some relevant concepts that might help describe this phenomenon: Hyperdimensional Encoding – The i
Moozonian News
meetnewbooks.com• Feb 20, 2025• 1 min read
Show HN: MeetNewBooks – Book recommendations for those who read for funHi HN,Like many projects here, this started as something I built for myself. I shared it with a few friends, and it grew from there.MeetNewBooks is a book recommendation app—a "find your next read" tool rather than a book tracking app.How it works:By Title: Enter a book you enjoyed, and we’ll suggest similar books. Depending on the book, you may see a mix of recommendations based on themes, genres, or tropes—combined with what other readers have enjoyed.Search by Keywords (Genre, Theme, Trope): Browse recommendations using filters like "epic fantasy," "coming of age," or "billionaire romances." No vectors or embeddings—just a straightforward Elasticsearch implementation.Suggestions Based on Recent Browsing: After you’ve looked at a few books, we’ll recommend others based on your browsing history. A "bulb" icon in the top right corner will show these suggestions.Personalized Recommendations (free, but requires signup): Save and rate books, and we’ll tailor suggestions as soon as we have
Sponsored