HF RL Explorer

a = Const(1) - Const(2)

a = Const(1) - Const(2): a task in MiMo-V2.6-RL-harbor-code: MiMo-V2.6-RL Code (Harbor) (Harbor dataset). The correct result here ( -1 ) is obviously not representable in an unsigned shape.

Part of FineEnvs/MiMo-V2.6-RL-harbor-code.