LibreChat

LibreChat

All-In-One AI Conversations with LibreChat LibreChat brings together the future of assistant AIs with the revolutionary technology of OpenAI’s ChatGPT. Celebrating the original styling, LibreChat gives you the ability to integrate multiple AI models. It also integrates and enhances original client features such as conversation and message search, prompt templates and plugins. With LibreChat, you…

Tiny volumetric display

Tiny volumetric display

1 Dec 2023Progress: Completed A tiny volumetric display!Video Demo Naturally you can’t really feel the volumetric effect on camera. It looks a lot more 3D in real life.Idea I was recently fortunate enough to find myself in the pub with some very creative and talented people. The discussion turned to electronic candles, and how one…

Anduril announces Roadrunner, jet-powered VTOL drone

Anduril announces Roadrunner, jet-powered VTOL drone

Roadrunner is a reusable, vertical take-off and landing (VTOL), operator-supervised Autonomous Air Vehicle (AAV) with twin turbojet engines and modular payload configurations that can support a variety of missions.Roadrunner-M is a high-explosive interceptor variant of Roadrunner built for ground-based air defense that can rapidly launch, identify, intercept, and destroy a wide variety of aerial threats…

Marker: Convert PDF to Markdown quickly with high accuracy

Marker: Convert PDF to Markdown quickly with high accuracy

Marker converts PDF, EPUB, and MOBI to markdown. It’s 10x faster than nougat, more accurate on most documents, and has low hallucination risk. Support for a range of PDF documents (optimized for books and scientific papers) Removes headers/footers/other artifacts Converts most equations to latex Formats code blocks and tables Support for multiple languages (although most…

Visual Anagrams: Generating optical illusions with diffusion models

Visual Anagrams: Generating optical illusions with diffusion models

University of Michigan Correspondence to: dgeng@umich.edu tl;dr: We use pretrained diffusion modelsto make optical illusions Miscellaneous Permutations Random Patch Permutations Method Our method is conceptually simple. We take an off-the-shelf diffusion model and use it to estimate the noise in different views or transformations, (v_i), of an image. The noise estimates are then aligned by…

Show HN: Australian Acoustic Observatory Search

The Australian Acoustic Observatory (https://acousticobservatory.org/) has 360 microphones across the continent, and over 2 million hours of audio. However, none of it is labeled: We want to make this enormous repository useful to researchers. We have found that researchers are often looking for 'hard' signals – specific call-types, birds with very little available training data,…