⌂ Research Index · tradebotsecrets research record · evidence-first, negatives included
Blind Driver Replay — BTC Trading System

Blind driver on a random track · controlled proof, replayed step by step

Driver Replay

Same track, four drivers. At every turn, the dashed gold ray is the driver's own guess — drawn from where it's standing, before the real turn is revealed. The road then extends in the real direction, green if the guess matched, red if it didn't. Nothing here is live-simulated; every driver is the actual champion genome trained in evolution/blind_driver_track_v1.py, replayed against one fresh, fixed track per variant. Toggle "drive by its own guesses" to switch from accuracy-scoring to a real physical drive: the car actually steers by its own belief instead of staying glued to the real road, and can wander within a tunable lane margin before it's flagged off-track. The 5 "Primitive" tabs are a different question entirely: those tracks have REAL structure (5 named, recurring patterns, not random turns), and the driver has to recognize which one is playing from an 8-step lookback — each one shown here is a track it never saw during training. Turning on lane-margin mode for those tabs reveals a real limitation, not a bug: high per-step turn accuracy (85-92%) still drifts badly once actually driving, because a single missed turn creates a permanent heading offset nothing ever corrects. The 5 "Combined" tabs fix exactly that — same lookback, PLUS real drift feedback, together: on-lane time jumps from 14.5% (lookback alone) to 86.8% overall.

Speed
Lane margin 5.0%
Press Play or drag the scrubber to begin.
Driver's guess, made before the real turn is known
Real road, guess was correct
Real road, guess was wrong
Real road, not yet reached

Vision
Track bias (continuation prob.)
Overall accuracy (this track)
Revealed so far
Running accuracy
Coin-flip baseline50%