Fly-NAF
Five Nights at Freddy's 1 played by the whole FlyWire v783 graph, 138,639 LIF neurons with their measured weights under a uniform x3 gain and nothing trained. LPLC2 and LC4 drive DNp01 to slam the doors, DNp09 raises the camera tablet, and GABAergic inhibitors silence DNp01 while it is up. On Pirate Cove, LC9 and LC31a drive DNp09 and a project-defined ten-second memory lets DNp04 shut the left door on Foxy. Builds on fly-brain, GPL v3. Full retained graph; no trained readout; screen input and mouse readout are hand-made. A starvation timer forces a look at any hallway unwatched for thirty seconds. Live panel of every soma. Windows; the Linux X11 backend has not run a night. No playable demo. Best run reached 5 AM on night 3.
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.