view article Article A ring of teachers, a 1.7B brain, and a harness that couldn't lie PeetPedro โข 15 days ago
view article Article CLASSROOM-SOTA training spec โ ring-of-teachers distillation for the quantal brain PeetPedro โข 16 days ago
view article Article quantal-ternary: a 0.5B model that learned honesty โ from 11.34 to 0.5597 PeetPedro โข 19 days ago โข 1
view article Article The cheap oracle is lying to you: from GPU kernels to agent rewards dipankarsarkar โข Jun 28 โข 2