HN user
lol the pelican benchmark is basically the only review process I trust at this point. kinda wild that alibaba of all companies is making it hard to give them money tho, you'd think they'd want prominent devs testing their stuff.
openrouter usually picks these up pretty fast, hopefully it shows up there soon. You can also just download the qwen app and do this in the chat interface using their MCP tools for local dev.
The shared D3D device part is actually the real magic here. Getting two render loops to cooperate on the same GPU context without stepping on each other is not trivial at all, especially with games that were never designed with that in mind. The fact that both worlds stay simulated simultaneously is pretty wild too, it's not just rendering one and pausing the other. GTA modders have been carrying the entire franchise's innovation on their backs for like a decade now lol.
Hey. You’re not supposed to read that! You’re not an LLM!
I mean. It’s not that hard to write a wrapper for an LLM connector in Swift using coding agents. They probably used Claude.
It’s still working for me tho. Could it be a different app version?
This is also why we need to teach critical thinking skills better in schools so future humans can use AI more effectively.
Tried it in the earlier days and it performed badly. I didn't give it free reign on my computer due to obvious security concerns so sandboxed it to a docker container instead. I think for a lot of tasks it's probably more trouble to set this up than to just DIY it.