Compare lens runs

Any two frozen runs — one model on two prompts, two checkpoints of one model, or two entirely different architectures on the same question.

ASteve Agentopen run

The capital of France is

2026-08-18 13:58 · MonumentalSystems/harmonic-gpt-128m-byte-agent-multiparty-lens@74c7dc09a1f9

positions
26 (+2 gen)
sites
2
lens agreement
—

completes: t

Where predictions settle — depth of commitment

Block 16 post-residual20
Block 17 post-residual6
BSteve Agentopen run

The capital of France is

2026-08-18 13:58 · MonumentalSystems/harmonic-gpt-128m-byte-agent-multiparty-lens@74c7dc09a1f9

positions
26 (+2 gen)
sites
2
lens agreement
—

completes: t

Where predictions settle — depth of commitment

Block 16 post-residual20
Block 17 post-residual6

Final readings, position by position

#A tokenA readsB tokenB readsagree
0ThTh=
1hehe=
2e e =
3 s s=
4coco=
5alal=
6papa=
7itit=
8tata=
9alal=
10l l =
11 o o=
12ofof=
13f f =
14 t t=
15FrFr=
16rara=
17anan=
18ncnc=
19cece=
20e e =
21 w w=
22isis=
23s s =
24 1 1=
25thth=