Bryn Bit retweeted
I spent a week ignoring everyone who said to switch engines.
Day 7, I pivot. You were right.
Building GTA 6 with a loop of AI agents. I spent the entire day on one thing: Swapping the project out of Godot and onto Unreal.
Yesterday I said I'd test Unity and probably skip Unreal. You guys pushed back hard: if you're serious about AAA, get on a real engine. so here we are.
What a full day of "just setup" actually looks like:
- Installed and configured Unreal
- Fought it onto a Mac build (the metal toolchain nearly ended me)
- Migrated the project over
- Got into a real Map and building assets
- Got a scene rendering with real lighting
First time this actually looks like GTA instead of a prototype of it.
I'm still wiring the agents into the editor and point the loop at a real engine.
Feedback is appreciated!
Day 6 of building GTA 6 with a loop of AI agents.
Today's drop:
- intro cinematic
- a real main menu (start game actually works)
- loading screen
- the whole front-end wired end to end.
So the look is done. Menu → load → you're in. it boots like a real AAA game.
We've been building in Godot the whole way, it's starting to show its limits on the AAA stuff. So this week I'm going to go test Unity to see if we can get the actual game into AAA stuff as well.
That's the part nobody measures. Every "best engine" take is about how it looks.
For a game built by a loop of agents, the only question that matters is which one they can read, edit, and push on their own.
Godot's good at that. Unity might be better, with way more assets off the market. I'm going to find out.
Agents still looping. Fable will be back soon!
I'll report back which engine they build faster in.
Bryn Bit retweeted
Bull thesis for $BountyBlox (If the trenches dont fuck it)
1. Roblox kids tell other roblox kids about how they can earn milk money
2. Roblox kids ape with parents credit/debit cards
3. Roblox kids get grounded
4. Now Roblox kids cant sell.
This quoted post is unavailable.