关于「向中间漂移,以及品味加上了什么」,《人机共生、并行智能体与指令信息论》给出的定量结论是什么?

结论:第一章说明向均值漂移来自以自身输出为食:反复对自己的样本重新拟合 100 代后,离散的中位数只剩 0.340;品味比数量更值钱,相关为 0.9 的人从 4 份草稿中挑选得到 0.926,高于相关为 0.3 的人从 64 份中挑选的 0.703。

数据口径:书中的智能体、比率、工时与价值均为示意模型;全部计算由书中程序生成;本书不是法律、财务或雇佣建议,也不对任何具体的 AI 产品作出断言。 书中以标注框区分已发表的证据、可运行的 Python 计算(16 段程序)、原典与作者的假说。

English version

对照数据表

下表数字由本章 Python 程序原样打印,可重新运行复现。 程序只用 Python 标准库与结论吻合的打印值: 0.3, 0.703, 0.9, 0.926, 64

drafts kE[max]rho 0.3rho 0.6rho 0.9
10.0000.0000.0000.000
20.5640.1690.3390.508
41.0290.3090.6180.926
81.4240.4270.8541.281
161.7660.5301.0601.589
642.3440.7031.4062.109
rho 0.9 with 4 drafts beats rho 0.3 with 64: True
查看完整验算程序
# Chapter 1. p02: Taste as a selection prior. A model produces k drafts
# whose true quality is standard normal. A person picks the one that
# looks best to them; their judgement correlates with true quality at
# rho. The expected true quality of the pick is rho times the expected
# maximum of k standard normals. Exact expected maxima by numerical
# integration; no sampling.
from math import erf, exp, pi, sqrt

def emax(k, lo=-8.0, hi=8.0, n=16000):
    h = (hi - lo) / n
    tot = 0.0
    for i in range(n):
        x = lo + (i + 0.5) * h
        pdf = exp(-x * x / 2) / sqrt(2 * pi)
        cdf = 0.5 * (1 + erf(x / sqrt(2)))
        tot += x * k * pdf * cdf ** (k - 1) * h
    return tot

if __name__ == "__main__":
    ks = (1, 2, 4, 8, 16, 64)
    em = {k: round(emax(k), 9) + 0.0 for k in ks}
    print("   drafts k   E[max]   rho 0.3   rho 0.6   rho 0.9")
    for k in ks:
        print("   {:8d}   {:6.3f}   {:7.3f}   {:7.3f}   {:7.3f}".format(
            k, em[k], 0.3 * em[k], 0.6 * em[k], 0.9 * em[k]))
    print("   rho 0.9 with 4 drafts beats rho 0.3 with 64: {}".format(
        0.9 * em[4] > 0.3 * em[64]))

唯一数据源与引用

范雅福(Fan, Y.). (2026). 《人机共生认知架构、多智能体并行流水线与指令信息论下界》第 1 章「向中间漂移,以及品味加上了什么」(版本 1.0.0). 5D Library. DOI 待发布

DOI 待发布 · 专著页正式发布后上线(本站暂无专著页) · 5DL-B-103 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026103,
  author    = {Fan, Yafu},
  title     = {Human-AI Symbiotic Cognition, Parallel Agent Pipelines and Prompt Information Bounds},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

本书其他章节结论