[charlie90]

https://github.com/charlesrw1/MultiplayerFps, its pretty easy. And this is just my hobbyist engine Ive been solo orchestrating agents with. If you had a team of ~10 AI-enabled devs, you could easily reach feature parity with Unity in a month or 2.

[strangecasts]

> Build: Let your agent figure it out

I'm sorry for going off on a random hobby project, but doing this in a C++ project - even if it is a standard Visual Studio solution - is "putting your whole mouth into the salsa dip"-level rude IMO, agent access should not be a prerequisite to build code!

[overgard]

If you really believe this, I highly encourage you to do it! Unity makes a lot of money, spread that among just 10 people and you'll be doing quite well, especially for a month of two of time spent. And more importantly you'll have the bragging rights of telling an internet commentator they're wrong!

The weird thing though is I see comments like this all the time, and I've yet to see anyone come back a month later as a billionaire so.. I'm going to keep my skepticism for the moment.

As an aside, bragging about lines of code as the first thing in your repo is a very weird flex. Lines of code are a cost, not an achievement, you (or your AI) has to maintain them and the more you have the more it costs.

FWIW good on you for making a thing, my goal isn't to trash your project, but from my perspective this does not look like a serious competitor to any game engine; it reminds me of projects I've seen from college students before AI (I don't meant that as an insult, I just don't find this as compelling evidence for your argument)