Compound Fork — Robotaxi × Humanoid deployment

Each cell = a joint scenario "Both branches fire". Cell intensity = total |Δ| across the 200 highest-conviction tradeable predictions vs their unconditional posterior. Joint probabilities approximated via log-odds combination (assumes conditional independence given the prediction — coarse but bounded). Click a cell to drill into the dominant single-fork view.

Pick two fork families

Rows (Robotaxi)Compute scaleEnergy / gridHumanoid deploymentRobotaxiAGIASI$1T+ IPOMars uncrewedAI pauseRecession
Cols (Humanoid deployment)Compute scaleEnergy / gridHumanoid deploymentRobotaxiAGIASI$1T+ IPOMars uncrewedAI pauseRecession
Robotaxi ↓ × Humanoid deployment
HUMANOID_FACTORY_2026
prior 40%
HUMANOID_ENTERPRISE_2028
prior 50%
HUMANOID_CONSUMER_2030
prior 20%
HUMANOID_MASS_2033
prior 10%
ROBOTAXI_TESLA_2026
prior 40%
135 claims · Σ|Δ| 19.30
135 claims · Σ|Δ| 19.21
134 claims · Σ|Δ| 19.34
134 claims · Σ|Δ| 19.19
ROBOTAXI_NATIONWIDE_2028
prior 45%
135 claims · Σ|Δ| 19.36
135 claims · Σ|Δ| 19.26
134 claims · Σ|Δ| 19.39
134 claims · Σ|Δ| 19.24
ROBOTAXI_MASS_2030
prior 30%
131 claims · Σ|Δ| 18.94
131 claims · Σ|Δ| 18.84
130 claims · Σ|Δ| 18.97
130 claims · Σ|Δ| 18.82
ROBOTAXI_DELAYED
prior 20%
135 claims · Σ|Δ| 19.37
135 claims · Σ|Δ| 19.27
134 claims · Σ|Δ| 19.40
134 claims · Σ|Δ| 19.25

Method note

Joint conditional probability is approximated via log-odds combination: logit(P(pred|A,B)) ≈ logit(P(pred|A)) + logit(P(pred|B)) − logit(P(pred)). This is the closed-form Bayesian update assuming A and B are conditionally independent given the prediction. It's correct when the two scenarios act on the prediction through different causal paths; it's pessimistic when they overlap. The exact joint requires running the Gibbs sampler with both scenarios clamped, which would be N×M=16 sampling runs (~12 minutes per refresh) instead of N+M=8 — a 2× cost for higher fidelity.