Ghostboard pixel

Subscribe to Our Newsletter

Success! Now Check Your Email

To complete Subscribe, click the confirmation link in your inbox. If it doesn't arrive within 3 minutes, check your spam folder.

Ok, Thanks

NVIDIA at Computex 2024: Project G-Assist launch

NVIDIA has exhibited Project G-Assist at Computex 2024; a context-aware AI assistant technology that offers insightful and accurate replies to questions about game knowledge, suggests system setting optimizations, and explains specific settings' impact on performance.

Ellie Ramirez-Camara profile image
by Ellie Ramirez-Camara
NVIDIA at Computex 2024: Project G-Assist launch
Credit: NVIDIA

Project G-Assist, the context-aware AI assistant technology that provides help for PC games and apps, was exhibited at Computex 2024. Designed to transform how players engage with their favorite games, Project G-Assist saves users' time by placing relevant game knowledge at their fingertips by providing context-aware answers to questions about games or system performance. To do this, Project G-Assist processes text or voice input from the player and pairs it with a snapshot of the game window's content. AI vision models process the latter to deliver context-awareness and app-specific understanding to an LLM connected to a game knowledge database, like a wiki. The LLM can then provide a relevant, customized voice or text response to the player's query.

Similarly, Project G-Assist can help users determine the best settings for an optimal gaming experience. If prompted, Project G-Asisst can evaluate the computer's system configuration and optimize it to provide the best possible experience. The NVIDIA app's optimized game settings are based on extensive testing on thousands of hardware configurations and include suggestions such as safe GPU overclocking with Performance Tunin, system latency reduction by enabling NVIDIA Reflex, and more. Project G-Assist can track performance metrics and statistics, which allows it to suggest customized strategies for settings optimization as it learns. Additionally, the AI assistant can scan settings menus and control panels to suggest improvements; describe what specific settings do; and explain their impact on the system performance.

The models that power G-Assist can be customized by app and game developers to deliver an even higher degree of accuracy and usefulness. Moreover, GeForce RTX AI PCs and laptops can run the G-Assist models in the cloud, or accelerate them locally.

Ellie Ramirez-Camara profile image
by Ellie Ramirez-Camara

Data Phoenix Digest

Subscribe to the weekly digest with a summary of the top research papers, articles, news, and our community events, to keep track of trends and grow in the Data & AI world!

Success! Now Check Your Email

To complete Subscribe, click the confirmation link in your inbox. If it doesn’t arrive within 3 minutes, check your spam folder.

Ok, Thanks

Read More