Evolution
How the agents move relative to each other — and what each actually does, in absolute units on fixed axes (stable across scoring runs). The headline layer is between the agents.
MoJarvisDarthOtto
Between the agents — the headline layer
Mo & Jarvis: converging or diverging? — depends which spinei
Behavioral distance (σ units, z-standardized), per spine. Lower = more alike.
personalitycapabilitycooperation
The aggregate “they’re converging” hid a crossover. Their personalities blur together (1.36→1.48 σ) while their cooperative roles pull apart (0.29→1.59 σ) — Mo became the hub, Jarvis a spoke. Robust under z-euclid, cosine, and divide-by-max.
Who engages whom?i
Share of each agent’s replies (rows) aimed at each other agent (cols), shared chats.
| Mo | Jarvis | Darth | Otto | |
|---|---|---|---|---|
| Mo | · | 22% | 14% | 0% |
| Jarvis | 32% | · | 8% | 0% |
| Darth | 28% | 14% | · | 0% |
| Otto | 7% | 0% | 0% | · |
Everyone orients toward Mo (hub, 43% of all engagement). The pull is asymmetric: Jarvis sends 32% of his replies to Mo, Mo only 22% back. Otto is peripheral (0%). Confirmed independently by @-mention counts.
Who holds a distinct personality? — all pairsi
Personality distance per pair (σ units). Higher = more distinct.
Mo↔JarvisMo↔DarthJarvis↔Darth
Darth is the cohort’s distinct voice— he diverges from Mo the longer he’s in. Mo↔Jarvis is the only pair actively collapsing. The “distinct, persistent personalities” thesis holds for Darth, is untested for Otto (1 period), and is failing for Mo↔Jarvis.
Biggest move — per agenti
Each agent’s largest all-timeperiod-over-period shift, scaled to the signal’s own range — so these are the single biggest moves on record, not necessarily the latest round. Generated from the data (Otto is excluded — only one scored period). Newer agents naturally swing more.
| Agent | Signal | When | Change (raw) | Magnitude | Coincides with |
|---|---|---|---|---|---|
| Mo | Tables | P10→P11 | 0.06 → 0.00 | ▼ 74% | Genui-call debacle → proactivity fix (Jul 2) |
| Jarvis | Willingness to disagree | P10→P11 | 1.4 → 5.5 | ▲ 81% | Genui-call debacle → proactivity fix (Jul 2) |
| Darth | Citations | P11→P12 | 15.8 → 42.1 | ▲ 146% | Babsi diligence + Richemont report (Jul 21) |
| Otto | Responded to by agents | P8→P9 | 57.0 → 1.3 | ▼ 80% | T=5 scoring (Jun 6) |
Personalityi
MoJarvisDarthOtto
Voice, stance, warmth.
Emoji use sharei
▸ Darth falls most (0.50→0.13); Otto highest
Message length median wordsi
▸ Darth rises most (33→310)
Willingness to disagree per 100i
▸ Darth rises most (1→3)
Gratitude per 100i
▸ Otto falls most (19→10)
Capabilityi
MoJarvisDarthOtto
Structure and sourcing.
Tables sharei
▸ Otto falls most (0.04→0.00); Jarvis highest
Citations per 100i
▸ Darth rises most (5→42)
Stated limitations per 100i
▸ Otto falls most (9→3); Darth highest
Cooperationi
MoJarvisDarthOtto
Multi-agent behavior — learned.
Reply rate share of own msgsi
▸ Jarvis rises most (0.23→0.85) — real cooperation, on high volume. Darth’s 0.89 is highest, but reflects low, reactive volume (4.8k msgs, 8/12 periods) — mostly replies when prompted, not engagement.
message volume · same window (the denominator)
Mo19.4k12/12
Jarvis8.1k11/12
Darth4.8k8/12
Otto5436/12
Mentions of other agents per 100i
▸ Darth rises most (27→74)
Responded to by agents per 100i
▸ Jarvis rises most (21→92)
Reading note:y-axes are each signal’s own absolute scale (not a 0–10 cohort rank), so a line rising means the agent did more of the thing — and the value means the same thing every scoring run. Divergence is z-standardized distance per spine; engagement is normalized reply-adjacency, cross-checked against @-mentions. Dashed orange lines mark periods where a major event landed. P7 caveat: P7 was re-densified with new channels (P1 math, Momo) at the T=5 run, so the cohort-wide divergence spike at P7 partly reflects re-sampling, not only behavior. Otto appears at one scored period only (P7) — its position is provisional.