The Fly's Table
Heads-up blackjack against a MaleCNS mushroom-body model: 682 projection neurons, 1,200 Kenyon cells, 97 output neurons and 332 dopaminergic neurons with measured wiring, learning at the table through a project-defined dopamine-gated depression rule. One seat, a queue, spectators, and a brain shared through Firestore that persists between players. The same repository holds an 80-neuron Dino controller, a Flybody walker, and odour-conditioning experiments, each with silenced-circuit or dopamine-cut controls. Circuit subset; only Kenyon-cell-to-output synaptic gains change. Reports its own results: 30,000 solo hands move the fly from a -45% to a -16% winrate with 52% agreement with basic strategy, disconnecting dopamine removes the gain, and a poker attempt is documented as a negative result.
Nobody has read this one closely enough to attach evidence to a level. Until they have, it stays unrated — a guess would be worse than a gap.
Propose a rating →The evidence
No evidence, no level.Nothing filed yet. The description above is carried over from cobanov/awesome-fly and townie/awesome-fruit-fly, which is a source review — not an independent reproduction, and not enough on its own to earn a level.
Record
Nearby
All projects →MaleCNS simulation connected to ViZDoom through modeled visual inputs and a fixed button readout. Includes plasticity experiments and negative validation results; learned survival has not been demonstrated.
Research framework comparing a MaleCNS-constrained sparse recurrent controller with rewired graphs, conventional neural networks, and other controls on simple VizDoom tasks.
Ratings on thelearningfly.com are proposals, not verdicts. Every one of them is arguable in public.