Nvidia’s Project G-Assist is among the few instances within the final yr or in order that any of the massive gaming firms have name-dropped AI and I’ve truly seen the imaginative and prescient. A chatbot/diagnostic device that reads your system and offers recommendation on easy methods to higher optimise it appears intuitively like one thing that would truly be helpful
Loads of the issue with video games having bigger and bigger settings menus is that it might probably all really feel a tad too granular. Do you flip one choice to get 1 fps larger, or do you go for a barely nicer texture? Are all of your elements operating on the speeds and temps they need to be, and the way would you recognize if not? Tinkering is among the greatest elements of proudly owning a PC, however that pleasure lies within the choice to take action—not the duty.
Well, you probably have a desktop RTX 20-, 30-, or 40-series card, you possibly can obtain G-Assist straight from the Nvidia app to assist out. Or no less than that is the hope. The program is in model 0.1.9, and notes that it is fairly experimental in each the Nvidia app and in G-Assist itself. Should Nvidia proceed to work on it, which it certainly will, it’ll probably get higher with time. The firm has already deliberate a hackathon to work on plugins for the software program, however ended up extending the deadline.
As it’s technically accessible to put in, I assumed I’d put it to the check.
Once put in, I want solely press ‘Alt + G’ to carry up a chatbox within the backside proper of my display. The chatbox popped up on my important monitor and turns into clear when enjoying video games.
While opening G-Assist is pretty straightforward, I did run into some hassle closing it. Minimising removes it from the display, but it surely has no icon on the taskbar, and it is just about all the time operating. You cannot shut it off simply, and even closing the app by way of Task Manager did not see it gone for good. It mechanically opened itself up once more proper after.
The Nvidia App often takes up between 100 MB to 150 MB of RAM utilization, which is barely a couple of third of what Slack calls for proper now, and about 15% of what Google Chrome calls for (do not decide me, I take pleasure in having a number of tabs open). However, this spiked as much as 1000 MB and round 10% of CPU in operation. Built on Meta’s Llama 3.1 LLM, it runs domestically (on machine), which might clarify a few of how resource-intensive it’s. Though you’ll count on it to be tougher in your GPU than your CPU, seeing who made it. It simply has to perform effectively sufficient to justify the utilization.
I assumed Black Myth: Wukong to be the very best first check of G-Assist, being a superb benchmark for displaying off Nvidia tech with DLSS and a recreation that advantages from clean frames per second.
After asking G-Assist to optimise my rig to run Wukong, it assured me that “Black Myth: Wukong has been optimised successfully. This will take effect from the next game launch”. Finding this reply a bit obscure, I requested it what optimisations it did, to which it replied, “Based on the provided information, I did not perform any optimisations”.
Oh, okay. Great. Thanks, G-Assist.
What the chatbot did do, nonetheless, was inform me to replace to Nvidia GeForce driver 576.40. This is often stable recommendation—up-to-date drivers make for a cheerful gaming PC—aside from the truth that I had put in these actual drivers initially of May. This outdated steerage was inadvertently a fairly good reminder to get driver 577.00, which launched a couple of days in the past. So, I suppose a cheerful reminder in a roundabout means..
As a check, I informed G-Assist that Wukong was operating uneven, but it surely refused to repair my imaginary drawback. G-Assist saved telling me I wasn’t operating a recreation in any respect. After repeated failed makes an attempt at convincing the bot that I used to be, the truth is, enjoying Black Myth: Wukong, my spirit was damaged and I gave up momentarily.
Third instances the allure, I assumed. After wandering round a bit and enjoying the sport slightly, I mentioned I used to be operating Black Myth Wukong, and it informed me, “Sorry I missed that! Can you please repeat?” The thought of a bot having an excuse like ‘lacking’ one thing I’ve typed makes my head spin, however I ignored that for now and informed it ‘My recreation is operating uneven. Could you repair that?”
The sage advice G-Assist gave me? “Model load error. Can you please repeat?” Classic. Ironically, moments after this, the game did start to perform poorly, and I had to use Google instead.
Another reason I chose Black Myth: Wukong specifically is that it’s an Nvidia-optimised game. It has good Multi Frame Generation (MFG) support and was on the cover of a set of new Nvidia drivers when it launched. It’s also become a bit of a poster child for Nvidia because it’s both popular and looks great in motion. The speed of the game makes a justification for DLSS, specifically DLSS4.
In Red Dead Redemption 2, after failing to see that I was playing the game and refusing to give any advice, the ‘Alt+G’ shortcut simply stopped working. Zero for two now. This bug was so persistent that I had to shut down G-Assist in Task Manager and boot it up again.
This didn’t fix my problem as it got stuck ‘initialising G-Assist’, and it failed to initialise over the 15 minutes I spent waiting. It was hogging up 500 MB of memory and around 7% of my CPU this whole time. Immediately after booting up the chatbot while Playing Red Dead Redemption 2, I noticed some stuttering but I’m unsure if this is directly related. RDR2 can be a bit of a finicky game and it definitely doesn’t like when you move out of the game and into a different tab.
After resetting the Nvidia app, it prompted me to update to version 0.1.13, which seemed to fix my problem of it not initialising.
Booting up Baldur’s Gate 3, G-Assist once again told me it had made optimisations it hadn’t and recommended old Nvidia drivers. It didn’t at any point mention specific graphics settings in Baldur’s Gate 3, though it did say “alter the in-game graphics settings to stability efficiency and visible high quality”. Which settings to adjust is anyone’s guess. I had the audacity to ask it which settings I should change based on my rig, and it told me “that will help you with this, you must be operating a recreation”. Zero for three.
So, I wouldn’t use it in games right now. However, it can access system information quickly and can chart CPU and GPU utilisation. This is neat, but once again, held back a little. This charting only happens over a small period of time and includes the ramping of resources to run G-Assist. That’s when it works at least. Also it’s not an entirely novel feature—a litany of other third-party applications can do this. Oh and Task Manager.
The chatbot offers up a few prompts on boot, like the charting option above or asking it to tell you more about your rig. One other option, “What is DLSS 4?”, took one minute and 56 seconds for the chatbot to answer. Its reply: “Sorry I missed that! Can you please repeat?”.
I asked this same question a few days prior and got a sufficient, if a little self-referential, answer. “DLSS 4 makes use of transformer fashions to generate new pixels by analysing the complete body, not simply localised context, not like earlier variations. This permits for extra correct and detailed picture reconstruction, leading to improved efficiency and picture high quality”. This answer requires you to know the basics of DLSS, but I guess it’s not wrong.
From my time testing, both when it worked as intended and not at all, all I can think is that almost all of my problems were more efficiently and accurately answered by Google. After resetting my PC, updating the app, turning everything off and on again, I just couldn’t get it to run stably. The idea of optimising your rig in a moment or diagnosing technical problems is pretty great, but all I got using G-Assist was more technical problems. I didn’t even get a lousy shirt with it.
Best gaming rigs 2025