top of page

rhino.ai research

Field notes

Experiments from the rhino.ai research team.

+9.7

points of macro-F1 ahead of Jev 1.14 on Banking77, with rules and concept vectors

0

GPUs needed

0.26 ms

per message, rules only

  FEATURED  DECISION COMPILATION · Benchmark

Crafted Decision Model: Beating Jev without a GPU

Decision Compilation turns experts' past decisions into rules and concept vectors, encoded straight into a network's weights with no training run. It scores 89.6% macro-F1 on Banking77 and runs on an ordinary CPU.

Banking77 · vs Jev 1.14   Nov 2026

15.6×

less compute per update: about 1.4 PFLOP to write ten facts through the 1.7B, against about 22 PFLOP through the 27B

11% → 73%

in wordings its reader never trained on

0.0

benchmark change after the writes

MODEL MEMORY · Benchmark

Cutting Training Costs 16x with Universal Engram Memory

A 1.7B model writes new facts into a shared memory table, and a frozen 27B model answers questions about them in wordings and formats it has never seen. Only the small model runs during the update.

Qwen3-1.7B writes, Qwen3.8-27B reads   Nov 12, 2026

bottom of page