Edmund Phelps, a Nobel prize-winning economist, is not alive to defend himself against this Breitbart article claiming to be based on his ideas:

This is where incoming Fed chairman Kevin Warsh’s argument about artificial intelligence and monetary policy fits naturally. Warsh has argued that AI represents a genuine supply-side productivity shock, not merely demand-pull inflation dressed up as growth. If that’s right, then accommodating those gains with lower interest rates isn’t a concession to inflation. It’s a recognition that the economy’s supply capacity is improving.

Under a Phelpsian framework, the policy goal should be to let productivity gains flow through the economy without forcing an unnecessary contraction. Rate cuts in this setting aren’t simply “loose money.” They can be the mechanism that prevents firms from overreacting to realized productivity gains by pulling back too sharply on hiring and investment.

This also explains why the tight labor market may be protective against recession rather than a precursor to it. In the standard story, a productivity acceleration can be dangerous because it follows a period of overexpansion. Firms hired in anticipation of the boom, and when productivity finally arrives, they discover they no longer need as much labor. Layoffs ensue, consumer confidence cracks, spending falls, and the risk of a recession becomes large.

This sounds kind of smart-ish, but I was skeptical because of the source. Phelps’s main ideas were about expectations of the future, true, but it seemed to me that this was likely to be a twisting of his ideas to meet a desired political end, rather than a serious analysis.

Since Phelps is not around to defend his ideas, I asked Gemini to assume his persona and write a response. Here is what she said:

It is flattering, I suppose, to see my theories invoked, but this argument entirely misapprehends the mechanics of both expectations and capital. If artificial intelligence is truly about to unleash a massive, structural leap in total factor productivity, the natural rate of interest must rise, not fall. When an economy anticipates a surge of genuine, grassroots dynamism—moving beyond the mechanical, exogenous growth of standard Solow models—firms aggressively seek capital today to capture those future gains. If a central bank artificially suppresses interest rates in the face of that surging demand, it does not foster innovation; it merely ignites asset bubbles and distorts the very market signals that tinkerers and entrepreneurs rely upon.

Furthermore, the author has forgotten the most crucial lesson of the expectations-augmented Phillips curve. You cannot placate the labor market with cheap money today by promising them a technological supply miracle tomorrow. If the Federal Reserve cuts rates in an already tight market, businesses and workers will instantly observe the monetary expansion and update their inflation expectations, driving up prices and wages immediately. The inflation takes root long before the first AI efficiency is ever deployed. True mass flourishing requires the discipline of real capital costs, not the illusion of a monetary free lunch.

Let’s imagine a case where we were actually observing increased productivity in real time because the AI technology is progressing and rolling out much faster that previous technologies like the “electrification, automobiles, radio, modern manufacturing” – which Breitbart mentions. In this case, we should also be seeing inflation expectations starting to shift toward deflation, and it would then make sense to lower interest rates and try to get more cash flowing through the system. But this can be done in real time in response to the signal. The argument that it can or should be done in advance would seem to be invalid. I don’t think Breitbart “overlooked” anything here, I just think this is an un-serious twisting of serious ideas, meant to fool people into supporting a preferred political agenda.