The software is labelled Beta, but is being pushed out to existing PCs anyway because… well… why not beta something in prod, it’s 2025 after all.
It appears in Game Bar, which is accessible from Windows Key + G. You may not have it yet as they are staging deployment. I’m not in Windows Insiders, but I have it installed — so it looks like the roll out is becoming wide. Note that I had uninstalled Copilot from my PC… but Gaming Copilot silently installed anyway.
It is similar to Recall, except not all the processing is done locally — it relies on the cloud. It screenshots gameplay, and then extracts elements of the screen (such as symbols and text) to work out what the player is doing. The idea is it can help you game, e.g. you can ask questions about what you’re doing in the game at a given moment.
lol, performance art. That’d be interesting. I’d watch too.
Plus 20K people did watch a fish play Pokemon.
Also now that I think about it, it shouldn’t be too hard to feed a vision model a specific subset, e.g. https://darksouls.wiki.fextralife.com/Weapons of the visuals of all equipment and only then give advice. There is so much hierarchical information in there, e.g. one doesn’t get an Elden Ring weapon in Dark Souls, or does not get an end of the game weapon (except with glitches) after 1h of play time, etc so it’s possible to narrow the search space a lot.
I imagine a lot can be done with just few curated sources. Now… again (and I apologize for repeating myself so much while possibly sounding pedantic), why? Like what’s the actual point?