Duplicate 3 Layers in Devstral-24B: Reasoning +245%, No Training.

Replicated David Ng's RYS method — duplicating layers 12-14 routes hidden states through the reasoning circuit twice, boosting BBH Logical Deduction from 0.22 to 0.76 and GSM8K from 0.48 to 0.64. Zero training, no weight changes. Same technique on Qwen2.5-Coder-32B improved reasoning probes by 23%. Discovered on two AMD consumer GPUs in one evening. GitHub