NVIDIA Project G-Assist - your in-game RTX AI Assistant for guides, tips, and overclocking

At Computex last year, NVIDIA showcased a glimpse at the future of gaming with a real-time NVIDIA ACE demonstration of a cyberpunk-style game scenario in which you could fully interact (with voice) with an AI-driven NPC to ask narrative-specific questions or anything else and get dynamic responses.

With speech recognition and Audio2Face animation, the technology has evolved and become more impressive in the following months. At Computex 2024, NVIDIA is presenting game-specific AI technology called Project G-Assist, an "RTX-powered AI assistant technology demo that provides context-aware help for PC games and apps."

How this works is fascinating. Take a game like ARK: Survival Ascended; you can ask for help on where to find resources and offer some tips on building the perfect base and how to overcome a boss or enemy. You can go beyond that and ask Project G-Assist to help optimize the game's settings so you can hit a steady 60 FPS. Very cool.

You can also ask G-Assist about performance metrics like frame rates and latency to see how things are running. It can even help you safely overclock your GeForce RTX GPU.

ARK: Survival Ascended is a real-world example of what Project G-Assist can do (the technology is still in development), as NVIDIA has partnered with Studio Wildcard to demo the technology with ARK: Survival Ascended. Essentially, the model is trained on game-specific data while seeing everything happening on screen (something that's not as controversial as Microsoft's screenshotting Recall feature for Copilot+ PCs).

"Project G-Assist can help answer questions about creatures, items, lore, objectives, difficult bosses, and more," NVIDIA explains. "Because Project G-Assist is context-aware, it personalizes its responses to the player's game session. The LLM showcased in the tech demonstration is a foundational pre-trained model. It has not been fine-tuned to the game's content. Instead, the LLM draws knowledge from a vectorized local database containing curated content sourced from Studio Wildcard and their official Wiki."

"NVIDIA launched the era of AI PCs in 2018, with the release of RTX Tensor Core GPUs and DLSS technology," said Jason Paul, vice president of consumer AI at NVIDIA. "Now, with Project G-Assist and NVIDIA ACE, we're unlocking the next generation of AI-powered experiences for over 100 million RTX AI PC users."

Project G-Assist sounds like a potential in-game wiki, guide system, and everything else rolled into one. Stay tuned for our hands-on impressions on the Project G-Assist demo directly from Computex 2024 later this week.