What does Bicameral AI Architecture conclude, in numbers, about “Correlated Errors: Where the Second Model's Gain Comes From”?
Answer: Chapter 1 uses a Gaussian copula to show that, at illustrative error rates, the second model's gain is 0.0880 at a latent correlation of 0 and only 0.0243 at 0.9, and that a weaker but different reviewer leaks only 0.498 of what a seemingly powerful look-alike leaks.
Scope of the numbers: Its parameters are illustrative; all calculations are generated by its programs; "bicameral" is an engineering metaphor and no model is claimed to have awareness; the book is not personalised business or engineering advice. Marked boxes separate published evidence, runnable Python calculations (23 programs), classical sources and the author's hypotheses.
Data table
The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 0.0243, 0.0880, 0.9
| A. p_a 0.10, p_b 0.12, q_same 0.60, gate miss 0.05 | |
| N | 40,000 simulated tasks per rho (seed 41001) |
| rho both(exact) both(MC) | leak: single agree veto gate | fr_veto | |
| 0.0 | 0.0120 0.0117 | 0.1000 0.0072 0.0120 0.0050 | 0.1080 |
| 0.1 | 0.0158 0.0163 | 0.1000 0.0095 0.0158 0.0050 | 0.1042 |
| 0.2 | 0.0201 0.0197 | 0.1000 0.0121 0.0201 0.0050 | 0.0999 |
| 0.3 | 0.0250 0.0261 | 0.1000 0.0150 0.0250 0.0050 | 0.0950 |
| 0.4 | 0.0305 0.0307 | 0.1000 0.0183 0.0305 0.0050 | 0.0895 |
| 0.5 | 0.0368 0.0358 | 0.1000 0.0221 0.0368 0.0050 | 0.0832 |
| 0.6 | 0.0440 0.0435 | 0.1000 0.0264 0.0440 0.0050 | 0.0760 |
| 0.7 | 0.0523 0.0520 | 0.1000 0.0314 0.0523 0.0050 | 0.0677 |
| 0.8 | 0.0624 0.0629 | 0.1000 0.0375 0.0624 0.0050 | 0.0576 |
| 0.9 | 0.0757 0.0751 | 0.1000 0.0454 0.0757 0.0050 | 0.0443 |
| B. gain of the second model (single - veto): rho 0 0.0880, rho 0.9 0.0243 | |
| share of the rho-0 gain left at rho 0.9 | 0.276 |
| rho 0.99: leak veto 0.0965, gain 0.0035 | |
| C. veto + gate at rho 0 0.00060, at rho 0.9 0.00379 |
Show the full program
# Chapter 1. p11: correlated errors of two models via a Gaussian copula.
# Model A errs with p_a, model B with p_b; latent normals with
# correlation rho are thresholded at the inverse normal of each rate.
# Four release rules: single A; consensus (release only if A and B
# agree; when both err they agree with prob Q_SAME); veto (B reviews
# A and blocks when it disagrees); single A plus a deterministic gate
# with miss rate G. Leak = wrong output released. False reject =
# right output blocked. All rates are illustrative, not measured.
import math
import random
from statistics import NormalDist
P_A, P_B, Q_SAME, G = 0.10, 0.12, 0.60, 0.05
N = 40000
ND = NormalDist()
def both_wrong(pa, pb, rho, steps=1600):
# exact P(Z1 < a, Z2 < b) by a one-factor integral (Simpson rule)
a, b = ND.inv_cdf(pa), ND.inv_cdf(pb)
if rho <= 0.0:
return pa * pb
s, r = math.sqrt(rho), math.sqrt(1.0 - rho)
lo, hi = -8.0, 8.0
h = (hi - lo) / steps
terms = []
for i in range(steps + 1):
f = lo + i * h
w = 1 if i in (0, steps) else (4 if i % 2 else 2)
v = ND.pdf(f) * ND.cdf((a - s * f) / r) * ND.cdf((b - s * f) / r)
terms.append(w * v)
return math.fsum(terms) * h / 3.0
def simulate(rho, rng):
a, b = ND.inv_cdf(P_A), ND.inv_cdf(P_B)
s, r = math.sqrt(rho), math.sqrt(1.0 - rho)
n11 = n10 = 0
for _ in range(N):
f = rng.gauss(0.0, 1.0)
za = s * f + r * rng.gauss(0.0, 1.0)
zb = s * f + r * rng.gauss(0.0, 1.0)
if za < a:
if zb < b:
n11 += 1
elif zb < b:
n10 += 1
return n11 / N, n10 / N
if __name__ == "__main__":
rng = random.Random(41001)
print("A. p_a {:.2f}, p_b {:.2f}, q_same {:.2f}, gate miss {:.2f}"
.format(P_A, P_B, Q_SAME, G))
print(" N = {:,} simulated tasks per rho (seed 41001)".format(N))
print(" rho both(exact) both(MC) | leak: single agree veto gate"
" | fr_veto")
for i in range(10):
rho = i / 10.0
bw = both_wrong(P_A, P_B, rho)
mc11, mc_rw = simulate(rho, rng)
right_bwrong = P_B - bw
print(" {:.1f} {:.4f} {:.4f} | {:.4f} {:.4f} {:.4f}"
" {:.4f} | {:.4f}".format(rho, bw, mc11, P_A,
Q_SAME * bw, bw, P_A * G,
right_bwrong))
b0, b9 = both_wrong(P_A, P_B, 0.0), both_wrong(P_A, P_B, 0.9)
g0, g9 = P_A - b0, P_A - b9
print("B. gain of the second model (single - veto): rho 0 {:.4f},"
" rho 0.9 {:.4f}".format(g0, g9))
print(" share of the rho-0 gain left at rho 0.9: {:.3f}"
.format(g9 / g0))
b99 = both_wrong(P_A, P_B, 0.99)
print(" rho 0.99: leak veto {:.4f}, gain {:.4f}".format(b99,
P_A - b99))
print("C. veto + gate at rho 0 {:.5f}, at rho 0.9 {:.5f}"
.format(b0 * G, b9 * G))Single source and citation
Fan, Y. (2026). Bicameral AI Architecture: Fusing Long-Context Holographic Strategy Models with Local Deterministic Execution Agents (Version 1.0.0), Chapter 1: Correlated Errors: Where the Second Model's Gain Comes From. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-410 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026410,
author = {Fan, Yafu},
title = {Bicameral AI Architecture: Fusing Long-Context Holographic Strategy Models with Local Deterministic Execution Agents},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 2 · Diversity Measures and the Ambiguity Decomposition: How Different Is Different Enough
- Chapter 3 · The Three-Stage Pipeline: Turning Errors into Intercepted Errors
- Chapter 4 · The Intent Translation Protocol: Slots, Ambiguity Entropy and Upper Bounds
- Chapter 5 · State-Sync Packets: Hash Chains, Version Vectors and Idempotency Keys
- Chapter 6 · Two-Way Correction: Gain, Noise and the Limits of Self-Correction
- Chapter 7 · Eastern and Western Classical Sources: Temple Reckoning, Breadth with Precision, and Friction
- Chapter 8 · The Empirical Loop: Field Tools and Checker Specifications