FlyAim
Full MaleCNS (166,700) closed-loop aiming, pre-registered. Wiring adds nothing versus a degree-preserving shuffle (mean target distance 412.5 px vs 430.9, p = 0.66); both sit farther from the target than uniform random (251.7 px). Frozen readout, a retrained readout, plasticity, behavior cloning, and DAgger all miss the gates. A later 6,098-cell compound-eye servo that holds the target bypasses the connectome. Local.
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 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.