Wayne Chi

@iamwaynechi

CS Ph.D. at @SCSatCMU. Funded by @NDSEG Fellowship. Intern @arena. Editor at blog.ml.cmu.edu.

Santa Clara

Pinned
Wayne Chi
@iamwaynechi
Feb 13
New preprint alert 🚨 Can LLM agents develop video games? We release GameDevBench, the first benchmark evaluating agentic game development in a game engine, Godot. We also present two simple multimodal feedback mechanisms that lead to immediate performance gains. /🧵
00:00
Wayne Chi
@iamwaynechi
Aug 8
🙏
Wayne Chi
@iamwaynechi
Aug 6
Muse Spark 1.2 is a frontier model for game development. It matches GPT-5.6-Sol, tying for third place. Earlier this year, Meta didn’t even have a model capable of making this leaderboard. A huge leap for the team—congrats on an amazing model!
Wayne Chi
@iamwaynechi
Aug 2
Game development is the next frontier. GameDevBench is the first step, but I'm very confident progress will be measured in some way related to game dev
Andrej Karpathy
@karpathy
Aug 2
We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for
00:00
Wayne Chi
@iamwaynechi
Jul 31
The cost efficiency of Luna for computer-use is incredible
Jing Yu Koh
@kohjingyu
Jul 30
We love our fast and cheap models for computer use!