Will Neural Scaling Laws Activate Jevons' Paradox in AI Labor Markets? A Time-Varying Elasticity of Substitution (VES) Analysis (2503.05816v2)

Abstract: We develop a formal economic framework to analyze whether neural scaling laws in artificial intelligence will activate Jevons' Paradox in labor markets, potentially leading to increased AI adoption and human labor substitution. By using a time-varying elasticity of substitution (VES) approach, we establish analytical conditions under which AI systems transition from complementing to substituting for human labor. Our model formalizes four interconnected mechanisms: (1) exponential growth in computational capacity ($C(t) = C(0) \cdot e^{g \cdot t}$); (2) logarithmic scaling of AI capabilities with computation ($\sigma(t) = \delta \cdot \ln(C(t)/C(0))$); (3) declining AI prices ($p_A(t) = p_A(0) \cdot e^{-d \cdot t}$); and (4) a resulting compound effect parameter ($\phi = \delta \cdot g$) that governs market transformation dynamics. We identify five distinct phases of AI market penetration, demonstrating that complete market transformation requires the elasticity of substitution to exceed unity ($\sigma > 1$), with the timing determined primarily by the compound parameter $\phi$ rather than price competition alone. These findings provide an analytical framing for evaluating industry claims about AI substitution effects, especially on the role of quality versus price in the technological transition.