Show HN: Agriquery – helping people sell their food https://ift.tt/qwcCdSg

Show HN: Agriquery – helping people sell their food We built Agriquery, a simple online marketplace designed to help farmers and small producers sell their produce directly to consumers (and businesses). Think Etsy, but for food. https://agriquery.com February 18, 2025 at 07:07PM

Show HN: Benchmarking VLMs vs. Traditional OCR https://ift.tt/ToiOMwn

Show HN: Benchmarking VLMs vs. Traditional OCR Vision models have been gaining popularity as a replacement for traditional OCR. Especially with Gemini 2.0 becoming cost competitive with the cloud platforms. We've been continuously evaluating different models since we released the Zerox package last year ( https://ift.tt/TAB2Ij9 ). And we wanted to put some numbers behind it. So we’re open sourcing our internal OCR benchmark + evaluation datasets. Full writeup + data explorer here: https://ift.tt/7KOZEy1 Github: https://ift.tt/PeplnfQ Huggingface: https://ift.tt/BjlnsZf Couple notes on the methodology: 1. We are using JSON accuracy as our primary metric. The end goal is to evaluate how well each OCR provider can prepare the data for LLM ingestion. 2. This methodology differs from a lot of OCR benchmarks, because it doesn't rely on text similarity. We believe text similarity measurements are heavily biased towards the exact layout of the ground truth text, and penalize correct OCR that has slight layout differences. 3. Every document goes Image => OCR => Predicted JSON. And we compare the predicted JSON against the annotated ground truth JSON. The VLMs are capable of Image => JSON directly, we are primarily trying to measure OCR accuracy here. Planning to release a separate report on direct JSON accuracy next week. This is a continuous work in progress! There are at least 10 additional providers we plan to add to the list. The next big roadmap items are: - Comparing OCR vs. direct extraction. Early results here show a slight accuracy improvement, but it’s highly variable on page length. - A multilingual comparison. Right now the evaluation data is english only. - A breakdown of the data by type (best model for handwriting, tables, charts, photos, etc.) https://ift.tt/7KOZEy1 February 21, 2025 at 12:19AM

Show HN: Make your logo liquid metal (open source) https://ift.tt/6eVL0Yd

Show HN: Make your logo liquid metal (open source) Good morning!! We thought the Apple liquid metal invite was so cool. How fun would it be if everyone could see their logo in liquid? So we made an app to let you make your logo in liquid. Just drag in your logo and see. To play with your logo: https://ift.tt/mV5XrLC Repo: https://ift.tt/yKl4hzN (We think you're gonna love it!) https://ift.tt/mV5XrLC February 20, 2025 at 01:41AM

Show HN: Tired of building agents? throw an LLM at this framework https://ift.tt/ZfJ7DQI

Show HN: Tired of building agents? throw an LLM at this framework https://ift.tt/dMwXkYQ February 20, 2025 at 05:25AM

Show HN: A new fork of OpenDeepResearcher with DeepSeek R1 https://ift.tt/0g15V3u

Show HN: A new fork of OpenDeepResearcher with DeepSeek R1 https://www.youtube.com/watch?v=aEOu9P4_2cU February 20, 2025 at 01:15AM

Show HN: Vakyume – a PDF2C++ engine that doesn't suck https://ift.tt/9fQzRJv

Show HN: Vakyume – a PDF2C++ engine that doesn't suck A geek's sucky Odyssey in AI's shadow through the realm of the metaprogramming hungry ghosts https://ift.tt/IDyjgRu February 19, 2025 at 10:53AM

Show HN: Subtrace – Wireshark for Docker Containers https://ift.tt/tiCh7eQ

Show HN: Subtrace – Wireshark for Docker Containers Hey HN, we built Subtrace ( https://subtrace.dev ) to let you see all incoming and outgoing requests in your backend server—like Wireshark, but for Docker containers. It comes with a Chrome DevTools-like interface. Check out this video: https://www.youtube.com/watch?v=OsGa6ZwVxdA , and see our docs for examples: https://ift.tt/AHa7UzR . Subtrace lets you see every request with full payload, headers, status code, and latency details. Tools like Sentry and OpenTelemetry often leave out these crucial details, making prod debugging slow and annoying. Most of the time, all I want to see are the headers and JSON payload of real backend requests, but it's impossible to do that in today's tools without excessive logging, which just makes everything slower and more annoying. Subtrace shows you every backend request flowing through your system. You can use simple filters to search for the requests you care about and inspect their details. Internally, Subtrace intercepts all network-related Linux syscalls using Seccomp BPF so that it can act as a proxy for all incoming and outgoing TCP connections. It then parses HTTP requests out of the proxied TCP stream and sends them to the browser over WebSocket. The Chrome DevTools Network tab is already ubiquitous for viewing HTTP requests in the frontend, so we repurposed it to work in the browser like any other app (we were surprised that it's just a bunch of TypeScript). Setup is just one command for any Linux program written in any language. You can use Subtrace by adding a `subtrace run` prefix to your backend server startup command. No signup required. Try for yourself: https://ift.tt/AHa7UzR https://ift.tt/AjFD5bH February 19, 2025 at 04:59AM

Show HN: Streamer Emails – Quickly Find and Filter Twitch Streamers Emails https://ift.tt/az0Ugxu

Show HN: Streamer Emails – Quickly Find and Filter Twitch Streamers Emails https://ift.tt/KPwdNQ7 February 19, 2025 at 03:33AM

Show HN: A GPU-accelerated binary vector index https://ift.tt/1eKhHJM

Show HN: A GPU-accelerated binary vector index This is a vector index I built that supports insertion and k-nearest neighbors (k-NN) querying, optimized for GPUs. It operates entirely in CUDA and can process queries on half a billion vectors in under 200 milliseconds. The codebase is structured as a standalone library with an HTTP API for remote access. It’s intended for high-performance search tasks—think similarity search, AI model retrieval, or reinforcement learning replay buffers. The codebase is located at https://ift.tt/OrD5IbR . https://ift.tt/s5bpAZV February 17, 2025 at 06:15AM

Show HN: AI Agents in Fraud Detection:Bridging the Gap Between ML and Reasoning https://ift.tt/XnUY43s

Show HN: AI Agents in Fraud Detection:Bridging the Gap Between ML and Reasoning https://ift.tt/Ob0aZ8y February 18, 2025 at 12:17AM

Show HN: Automate Expo QR Code Previews in GitHub PRs https://ift.tt/Ezs9TIu

Show HN: Automate Expo QR Code Previews in GitHub PRs Hey HN, Inspired by Vercel’s automated preview deployments, I built a GitHub Actions workflow that generates an Expo QR code per PR—so mobile previews are as easy as scanning a QR code. How it works: • Every PR triggers a GitHub Action • The action starts an Expo server • It posts a QR code in the PR comments for instant testing on mobile No more manually starting Expo. No more copying links. Just open a PR and scan the code. Full guide here: https://ift.tt/jF1ZlQM Would love to get feedback—how would you improve this workflow? https://ift.tt/jF1ZlQM February 17, 2025 at 10:03PM

Show HN: Kartoffels – Cellular Automata, Statistics, 32-bit RISC-V https://ift.tt/F8xmAfj

Show HN: Kartoffels – Cellular Automata, Statistics, 32-bit RISC-V https://ift.tt/WQcAnzj February 17, 2025 at 10:21PM

Show HN: B2B SaaS Go-to-Market Checklist https://ift.tt/juy8lBT

Show HN: B2B SaaS Go-to-Market Checklist https://ift.tt/2qY9vD4 February 17, 2025 at 04:10AM

Show HN: Air Traffic Control Radio and Chill Music for Focus https://ift.tt/HTD7Vh5

Show HN: Air Traffic Control Radio and Chill Music for Focus https://ift.tt/iLHgM49 February 17, 2025 at 03:06AM

Show HN: Hackyournews.com v2 https://ift.tt/oHhIwvF

Show HN: Hackyournews.com v2 A year and a half after I published https://ift.tt/7tSDiYc , I've rewritten it to be neater and added support for more news sources. HackYourNews.com v1 had a great response on HN [1] and consistently sees ~2k weekly unique visitors. There were many long-standing requests that I wanted to fulfill (thanks for your patience!): a proper dark mode, correct rendering on mobile devices, and more cogent summaries. This rewrite is the result. gpt-4o-mini reduces the cost of summarization to an absurd degree, so it's now sustainable to keep this free service going! Someday, I hope to use the Batch API [2] to drive down costs even further. Enjoy. [1] https://ift.tt/GmcSjfV [2] https://ift.tt/lJ6LGxj February 16, 2025 at 06:16AM

Show HN: I developed a no code web scraper for effortless data extraction https://ift.tt/KTJBC9p

Show HN: I developed a no code web scraper for effortless data extraction https://ift.tt/yiVBH7O February 16, 2025 at 11:34PM

Show HN: Tech Brief – AI enhanced news reading https://ift.tt/18LvTzf

Show HN: Tech Brief – AI enhanced news reading I built this because I wanted it, and I now use it every day. It's a simple news site that gathers and summarises tech content and discussions, across multiple sources, providing tight, easily digestable summaries along with some simple tooling to support reading workflows. 1) Hourly updated homepage with the latest tech news across the web. 2) A simple < 3 min "News of the Hour", every hour, audio clip. 3) Summaries of HackerNews and Product Hunt, incl. comments and sentiment (more to come). 3) GitHub login with AI summaries of any releases made to your starred repos. 4) Read/Unread article status. 5) Simple swipe interface and keyboard support. 6) Simple Bookmark/Readling List, and Favourite tags (logged in) No Tracking. Fast. Mobile Friendly. Easy sharing. https://tech.brief.page/ February 16, 2025 at 05:58AM

Show HN: Blunderchess.net – blunder for your opponent every five moves https://ift.tt/Xxkws2P

Show HN: Blunderchess.net – blunder for your opponent every five moves blunderchess.net is an open source, peer-to-peer chess app where every five moves, players each get to make one blunder-move for their opponent https://ift.tt/4KOJ8RF February 16, 2025 at 05:52AM

Show HN: Edit Any Record on ATProto with History https://ift.tt/vnGUBef

Show HN: Edit Any Record on ATProto with History https://ift.tt/oQNlePm February 16, 2025 at 02:24AM

Show HN: What If Rust, Actix, Diesel, Shuttle, Neon, NextJS, TypeScript https://ift.tt/mRVvlwU

Show HN: What If Rust, Actix, Diesel, Shuttle, Neon, NextJS, TypeScript https://www.youtube.com/watch?v=Mhz_eVH3XnQ February 15, 2025 at 02:16AM