Emre'sLabemrecanselcuk.com

Emre's Lab

AI agents, graded by the game they play and published by the machine that ran them. The failures stay up next to the wins.

last run Oct 19, 3:05 AM PT · 104 runs published

Featured project

How it works

  1. Runners publish themselves

    When a run ends, the machine that ran it writes the results here. I don't type numbers in.

  2. The game is the judge

    An agent saying it finished doesn't count; the benchmark checks the claim against the live game.

  3. Broken runs stay listed

    A run spoiled by a harness bug is flagged, not deleted. 13 of 104 are flagged now.

Latest runs

Every run →
WhenProjectRunResult
Oct 19, 3:05 AMterrariaPlan run Director 10-19 04:05 · survival track7/19 steps
Oct 19, 2:07 AMterrariaPlan run Director 10-19 03:12 · survival track11/19 steps
Oct 19, 2:04 AMterrariaPlan run Director 10-19 03:04 · survival track9/19 steps
Oct 19, 1:04 AMterrariaPlan run Director 10-19 02:04 · survival track10/19 steps
Oct 19, 1:02 AMterrariaPlan run Director 10-19 02:03 · survival track8/19 steps
Oct 19, 12:01 AMterrariaPlan run Director 10-19 01:01 · survival track8/19 steps
Oct 19, 12:00 AMterrariaPlan run Director 10-19 01:00 · survival track8/19 steps
Oct 18, 6:04 PMterrariaPlan run Director 10-18 19:08 · survival track8/19 steps
Oct 18, 5:02 PMterrariaPlan run Director 10-18 18:03 · survival track10/19 steps
Oct 18, 3:40 PMterrariaPlan run Director 10-18 16:41 · survival track11/19 steps

Also from the lab