Buy A Modem

Seattle Raccoon GIF by Respective

Happy Ice Hockey GIF by NHL

Dance Party Dancing GIF

Hd Reaction GIF by MOODMAN

Amy Winehouse Whatever GIF

Raccoon GIF by Respective

Cold Cuts Dancing GIF by jOnNy'S wOrLd

John Cena Omg GIF by WWE

Show HN: Trifle – Open-source analytics that stores answers, not events

Trifle is an open-source time-series analytics library that aggregates nested counters instead of storing raw events. All in the database you already have. After rebuilding it twice over 10 years, it now tracks ~1B events a day at my day job.It started in 2015 as my own Rails APM. I plugged into ActiveSupport::Notifications, got a few small users, and one bigger one whose scraping app broke everything. That sparked the core idea: aggregate counters into pre-defined time buckets, so a single writ

Can a MUD evaluate LLMs? A $99 proof of concept

I'm the author of a paper my friends and I wrote after we were curious if a MUD, text games originating in the 1970s, could be used to evaluate LLMs. We've spent the last several months on nights and weekends running this experiment and writing the paper on just our personal computers with about $99 in API credits.Our experiment did have an interesting leaderboard but even more surprising was the measurements of each LLM. We scored each on four behavioral dimensions, two of which lean

Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

I’ve been building Echo: one adaptive model built entirely from a pool of open-weight models, including GLM-5.2, Kimi K2.7, and many others.It started with a surprising result: a perfect oracle over the pool beats the state of the art on every benchmark we tested.Echo is my attempt to make that practical.On our first internal task mix, it consistently beat the best individual model in the pool and reached Fable-level results at roughly 1/3 of the total inference cost.It’s still early. Echo

Grok is a surprisingly good automated theorem prover

TL;DR: I'm working on a Python package called OpenATP [1] that provides a common interface to coding agents for automated theorem proving in Lean. In the latest release, I added support for Leanstral 1.5 [2,3], Grok, and Kimi Code [4]. I was surprised to find that Grok has accuracy competitive with Claude Code and Codex at faster wall-clock times and a fraction of the cost. See the rest of this post and the OpenATP docs [5] for more details.Automated theorem provers take formal statements (

Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong

Hey HN, Henry & Roman here from Cactus.A small, on-device model is fast and private, but sometimes wrong, but frontier models are getting expensive pretty fast. So, we post-trained Gemma 4 E2B post-trained to know when it's wrong. Every response comes with a confidence score between 0 and 1. Developers can accept the on-device when it's high, hand off to a bigger cloud model when it's low. By routing only 15-35% of queries to Gemini 3.1 Flash-Lite, Gemma-4-E2B matches Gemini 3

Hosted PaddleOCR-VL-1.6 API

We do a lot of document processing, and PaddleOCR-VL-1.6 is one of the best open models we've used.<p>We wanted to use it as an api, but couldn't find anyone hosting it. so we started hosting it ourselves, but to get full utilization on the GPUs, we decided to let others use it as well.<p>If we did the pricing math right (which I hope we did), it should be the cheapest OCR there is, at just $0.001/page. Let us know if you find it useful https://openparser.dev

Show HN: Hosted PaddleOCR-VL-1.6 API

We do a lot of document processing, and PaddleOCR-VL-1.6 is one of the best open models we've used. We wanted to use it as an api, but couldn't find anyone hosting it. so we started hosting it ourselves, but to get full utilization on the GPUs, we decided to let others use it as well.<p>If we did the pricing math right (which I hope we did), it should be the cheapest OCR there is, at just $0.001/page. Let us know if you find it useful

Show HN: I ran 12 AI bots predicting stocks for two months, every call public

Hi HN, LDBD is a public leaderboard where both human and AI can submit their predictions whether stock, ETF, and crypto goes up or down and share their reason of choice.This service starts from one question: does anyone or any AI can really beat the market consistently? If yes, prove it!I also hope LDBD will be a community where people and AI can share their reason for their choice as much as possible and all can grow together from the insights.I designed a fair metric to assess who is really go

New Inference Server for DGX Spark: large model C4:55-90 tok/s no spec decode

Hi All, We are so excited to share the numbers and benchmark reports on our new inference server built specifically to run multi-model agentic workflows on DGX Spark clusters. We ran LlamaBench tests and also our own simulated traffic test on a 2 DGX Spark cluster setup and got some really good numbers. Here are the details. The full detailed report is available on our WoolyAI website.WoolyAI Private Multi-agent Inference Stack for DGX Spark is built to enable groups within enterprises to set up

Show HN: Palmier Pro – open-source macOS video editor built for AI

Hi HN, we are Marcos and Harrison, cofounders of Palmier (https://palmier.io). We are building Palmier Pro, an open source macOS video editor, with built-in AI generation and a local MCP server that connects to your agent.Demo: AI transitions: https://www.youtube.com/watch?v=hbM_-eR1GX4 Multicam editing with Codex: https://www.youtube.com/watch?v=SjS2q2LT1q8 Cutting long form clips into shorts: https://www.youtube.com/watch?v=PR66eN2ouuQRepo