Editor’s note: This post is part of the AI Decoded series, which demystifies AI by making the technology more accessible and introduces new hardware, software, tools, and tools for GeForce RTX PC and NVIDIA RTX workstation users. Introducing acceleration.
Over the past year, our AI Decoded series has decoded all things AI, from simplifying the complexities of large-scale language models (LLMs) to highlighting the power of RTX AI PCs and workstations.
This roundup of the latest advances in AI focuses on how this technology is changing the way people write, game, learn, and connect online.
NVIDIA GeForce RTX GPUs give you the ability to deliver these experiences on your laptop, desktop, or workstation. They feature specialized AI Tensor Cores that can deliver over 1,300 trillion operations per second (TOPS) for cutting-edge performance in gaming, production, everyday productivity, and more. For workstations, NVIDIA RTX GPUs deliver over 1,400 TOPS for next-level AI acceleration and efficiency.
Unleash productivity and creativity with AI-powered chatbots
Earlier this year, AI Decoded investigated what an LLM is, why it’s important, and how to use it.
For many, tools like ChatGPT were their first introduction to AI. LLM-powered chatbots have transformed computing from basic rule-based interactions to dynamic conversations. They can suggest vacation ideas, write customer service emails, compose original poetry, and even write code for users.
Introduced in March, ChatRTX is a demo app that allows users to personalize GPT LLM with their own content such as documents, notes, and images.
With features like search augmented generation (RAG), NVIDIA TensorRT-LLM, and RTX acceleration, ChatRTX lets users quickly search and ask questions about their data. And because the app runs locally on your RTX PC or workstation, results are fast and private.
NVIDIA offers the widest selection of base models for enthusiasts and developers, including Gemma 2, Mistral, and Llama-3. These models can run locally on NVIDIA GeForce and RTX GPUs for fast and secure performance without relying on cloud services.
Download ChatRTX now.
Introducing RTX acceleration partner applications
AI is being incorporated into a growing number of apps and use cases, including games, content creation apps, software development, and productivity tools.
This expansion is driven by a wide selection of RTX-accelerated developer and community tools, software development kits, models, and frameworks, making it easier than ever to run models locally in common applications. I did.
October’s AI Decoded focuses on how Leo AI in Brave Browser, powered by NVIDIA RTX GPUs and the open source Ollama platform, lets users run local LLMs like Llama 3 directly on their RTX PC or workstation I guessed.
This local setup provides fast, responsive AI performance while preserving the privacy of user data without relying on the cloud. NVIDIA optimizations for tools like Ollama deliver performance for tasks like summarizing articles, answering questions, and extracting insights, all directly within the Brave browser. Users can switch between local and cloud models, giving them flexibility and control over their AI experience.
See Brave’s blog for easy steps to add local LLM support via Ollama. When configured to point to Ollama, Leo AI uses the locally hosted LLM for prompts and queries.
Agentic AI — enabling complex problem solving
Agenttic AI is the next frontier in AI and can autonomously solve complex multi-step problems using advanced reasoning and iterative planning.
AI Decoded investigated how the AI community is experimenting with technology to create smarter, more capable AI systems.
Partner applications like AnythingLLM demonstrate how AI can improve productivity and creativity beyond simple question answering. Users can leverage applications to deploy built-in agents that can tackle tasks such as searching the web and scheduling meetings.
AnythingLLM allows users to interact with documents through an intuitive interface, automate complex tasks with AI agents, and run advanced LLM locally. Harness the power of RTX GPUs for faster, smarter, and more responsive AI workflows, all within a single local desktop application. The application works offline, is fast and private, and allows you to use local data and tools that are typically not accessible with cloud-based solutions.
AnythingLLM’s Community Hub is a system that helps you control LLM behavior, discover slash commands to improve your productivity, and build specialized AI agent skills for your own workflows and custom tools. Prompts are easily accessible to everyone.
AnythingLLM fosters innovation and makes it easier to experiment with the latest technologies by allowing users to run agent AI workflows on their own systems with complete privacy.
AI decoded wrapped
Today, over 600 Windows apps and games are already running AI locally on over 100 million GeForce RTX AI PCs and workstations around the world, delivering fast, reliable, and low-latency performance. I am. Learn more about NVIDIA GeForce RTX AI PCs and NVIDIA RTX AI Workstations.
Watch NVIDIA Founder and CEO Jensen Huang’s CES keynote on January 6th to learn how modern AI is powering gaming, content creation, and development.
Generative AI is transforming gaming, video conferencing, and all kinds of interactive experiences. Subscribe to the AI Decoded newsletter to know what’s new and what’s next.
