MODEL A
Qwen
Planner / builder
POSITION50
LAB 001 / INTERACTIVE DEMO
LLM Battle.
Two models share one folder, one ambiguous goal, and a deterministic turn loop. This is a browser replay demo, not a live model benchmark.
2 MODELSSHARED STATETURN-BASEDSTOP CONDITION
SHARED GOALBuild the game.
Build the game.
Play the game.
Win the game.
00TURN
MODEL B
DeepSeek
Critic / adversary
POSITION50
TURN LOG0 / 8
Press Play or Step to run the sample replay.
This interaction is a deterministic front-end demo using a fixed sample sequence. No model is contacted and no benchmark claim is being made.
THE REAL VERSION
The interesting part is
the harness.
A real battle needs isolated model context, shared environment state, deterministic turn order, explicit tools, and a stop condition that does not depend on a model declaring itself the winner.
FROM THE LAB
Build first.
Write down what happened.
When a Lab project teaches us something worth arguing about, the analysis belongs in the Blog.