Show HN: I built the most over-engineered Deal With It emoji generator

This is a Deal With It GIF generator that allows users to create GIFs directly in their browser by uploading or pasting image URLs. The generator is made with passion by Igor Klimer and the source code is available on GitHub.

Read more

Adobe's new image rotation tool is one of the most impressive AI tools seen

Here is a summary of the text in a couple of sentences:

Adobe has unveiled a new AI-powered image rotation tool called "Project Turntable" that allows users to easily rotate 2D vector art in 3D while maintaining its original 2D appearance. The tool, developed by Adobe research scientist Zhiqin Chen, uses AI to fill in gaps in the image and is one of the most impressive AI concepts showcased at Adobe's MAX conference.

Read more

FTC announces "click-to-cancel" rule making it easier to cancel subscriptions

The Federal Trade Commission (FTC) has announced a final "Click-to-Cancel" rule that makes it easier for consumers to end recurring subscriptions and memberships. This rule requires companies to provide a clear and easy way for consumers to cancel their subscriptions, such as a prominent "cancel" button on their website or mobile app.

Read more

NotebookLM launches feature to customize and guide audio overviews

Here is a summary of the text in a couple of sentences:

Google has updated NotebookLM, a tool powered by Gemini 1.5, with new features including customizable Audio Overviews that allow users to provide instructions for AI hosts and listen to audio while working within the tool. Additionally, NotebookLM Business, an upcoming version offered via Google Workspace, will provide enhanced features for businesses, universities, and organizations, prioritizing data privacy and security.

Read more

Kagi Update: AI Image Filter for Search Results

Kagi's AI Image Filter feature aims to deliver high-quality, relevant search results by downranking AI-generated images and labeling them with a small badge or icon. Users can also filter out websites with AI-generated images from their search results, giving them more control over the content they see.

Read more

Cheating Automatic LLM Benchmarks

Researchers found that a "null model" that always outputs a constant response can achieve top-ranked win rates on popular automatic language model benchmarks, such as AlpacaEval 2.0, Arena-Hard-Auto, and MT-Bench. This highlights a vulnerability in these benchmarks and calls for the development of anti-cheating mechanisms to ensure reliable evaluation of language models.

ArXiv

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Model Swarms is a collaborative search algorithm that adapts large language models (LLMs) via swarm intelligence, allowing diverse LLM experts to work together to optimize a utility function and improve model performance. This approach offers tuning-free model adaptation, works well in low-data regimes, and outperforms existing model composition methods by up to 21.0% across various tasks and contexts.

ArXiv

From Commands to Prompts: LLM-Based Semantic File System for AIOS

Researchers propose an LLM-based semantic file system (LSFS) that enables users to interact with files through natural language prompts, improving usability and file management capabilities. LSFS incorporates a comprehensive API set and vector database to facilitate semantic file management, offering significant improvements over traditional file systems in terms of user convenience and accuracy.

ArXiv

The Energy Implications of AI Adoption

Researchers estimated that the adoption of Artificial Intelligence across US industries could lead to a 0.03% annual increase in energy consumption and a 0.02% annual increase in carbon dioxide emissions. The estimated increase in energy consumption and emissions ranges from 28 PJ and 896 ktCO$_2$ per year, respectively, to 0 and 272 ktCO$_2$ per year, respectively.

ArXiv

Data-Prep-Kit: getting your data ready for LLM application development

The Data Prep Kit (DPK) is an open-source data preparation toolkit designed to help users scale their data preparation for Large Language Model (LLM) development. DPK offers a highly scalable and extensible set of modules for transforming natural language and code data, allowing users to prepare data on a local machine or a cluster with thousands of CPU cores.

ArXiv

AI PCs Aren't Good at AI: The CPU Beats the NPU

We benchmarked Qualcomm's NPU on a Microsoft Surface Tablet and found that it only achieved 1.3% of its claimed 45 Teraops/s performance. The benchmark measured the latency of running a simple model on the CPU and NPU, with the NPU achieving 225 Gigaops and 573 Gigaops in two different approaches.

Repo

Show HN: Tamagotchi-like characters for AI assistants in JavaScript

This project is inspired by the classic Tamagotchi device, featuring a virtual character that can be controlled through buttons or an AI assistant. The character can be used in two modes: manual mode, where actions are performed by clicking buttons, and AI-controlled mode, where the character is automatically updated by an AI assistant.

Repo

Nvidia Outperforms GPT-4o with Open Source Model

Arena-Hard-Auto is an automatic evaluation tool for instruction-tuned LLMs that contains 500 challenging user queries sourced from Chatbot Arena. It has the highest correlation and separability to Chatbot Arena among popular open-ended LLM benchmarks.

Repo

Show HN: Arch – an intelligent prompt gateway built on Envoy

Arch is an intelligent Layer 7 gateway designed to protect, observe, and personalize Large Language Model (LLM) applications by handling undifferentiated tasks such as prompt detection, API calling, and observability. It is built on Envoy Proxy and features function calling, prompt guardrails, traffic management, and standards-based observability.

Repo

Out-of-Distribution Machine Learning

This repository provides a comprehensive resource for out-of-distribution (OOD) detection, robustness, and generalization in machine learning/deep learning. It aims to address critical challenges in modern AI systems that encounter data differing from their training distribution, leading to unexpected failures.

Repo