CalibratedDecisions.

Repo · Games & real time

LLM Chess: jev-latest

Jev played 80 games in a chess benchmark and made no illegal move.

Open github.com ↗

From the repository

LLM Chess - evaluating Large Language Models' reasoning and instruction-following abilities by simulating chess games

The decision Jev makes

Choose a legal move, a lane or an NPC reaction each turn.

Where it fits

Games are a stress test for decision speed. Jev picks the next move from the legal ones, fast enough for arcade games and deep enough for chess and strategy. All 256 games & real time projects →

Related projects