FlyTris.
A tiny player at the controls.
The scorebook.
Three-minute ranked matches. Score = lines cleared; pieces placed break ties.
Human vs. fly
Humans 0 lines
Fly 0 lines
No completed matches yet.The fly’s brain stays the same at every pace. Faster play allows more decisions before time runs out.
Chart totals include every recorded match in the selected window and difficulty.
Easy800 ms gravity · fly every 5s
| Player / date | Human | Fly |
|---|
Medium500 ms gravity · fly every 3s
| Player / date | Human | Fly |
|---|
Hard250 ms gravity · fly every 1.5s
| Player / date | Human | Fly |
|---|
Top 10 human scores per difficulty, paired with the fly’s score from the same match. Dates use your local time. Names are player-provided.
Learning, measured.
| Run | Before | After | Gain [95% CI] | Training |
|---|---|---|---|---|
| 11 | 0.12 | 40.71 | +40.58 [33.33, 48.62] | 1.1 min |
| 22 | 7.46 | 103.83 | +96.38 [86.75, 103.88] | 1.4 min |
| 33 | 0.08 | 68.58 | +68.50 [58.33, 78.50] | 1.3 min |
Mean lines cleared on identical, unseen piece sequences. This replay is the first held-out game from the first training run.
What actually learns?
Board features enter a fixed fly-derived spiking circuit. Eight learned output weights choose a placement from its activity.
The fly animation illustrates recorded decisions. It is not a biomechanical simulation. Removing recurrent connections did not consistently hurt performance in these trials, so fly wiring has not been shown to be essential.