Every node broadcasts a signed delta and every receiver verifies it before counting it. This shows what was counted and how many nodes it came from. Measured figures and projections are labelled separately, and a projection with no basis is not shown.
Ten nodes: Expert routing across models with different blind spots.
Stages are a hypothesis from hive_benchmark_prover.py, unmeasured. The node count is measured.Every node counted here runs Nunba on its owner's own machine. The next threshold is 7 nodes away, and yours would be one of them.
1
One node
A single model, running locally.
3
Three nodes
The first threshold: does the sum beat the single?
10
Ten nodes
Expert routing across models with different blind spots.
100
A hundred
Network mixture-of-experts.
1,000
A thousand
Generate, review, test as separable roles.
10,000
Ten thousand
Hive learning compounds across the population.
100,000
A hundred thousand
Beyond what one model does.
| Node | Index | Growth | Agents | Last heard | |
|---|---|---|---|---|---|
| 2c48f50bdf6b (serving this page) | -- | -- | 0 | 60s ago | |
| 8abb29215b1e | 0.000 | 1.000 | 1 | 88s ago | |
| fee9f14a481f | -- | -- | 0 | 2 h ago | stale |