A NY State Senate proposed bill (Senate Bill S7263) would

prohibit a chatbot to give substantive responses; information, or advice or take any action which, if taken by a natural person, would constitute unauthorized practice or unauthorized use of a professional title as a crime in relation to professions who licensure is governed by the education law or the judiciary law.

Claude, what do you think of the legal logic of this bill?

The legal logic is shaky. The bill’s operative test asks whether a chatbot’s output, “if taken by a natural person, would constitute a crime” under New York’s unauthorized practice statutes. But those statutes set a high bar — mere advice-giving by a layperson is not criminal; what’s prohibited is holding yourself out as a licensed professional while charging fees. Your neighbor who happens to be a doctor can tell you what he thinks your rash is. A retired lawyer can walk you through a lease. None of that is a crime. So either the bill is mostly toothless — most AI responses wouldn’t meet the criminal threshold — or courts will interpret “substantive advice” far more expansively than the underlying statutes warrant, effectively creating a new and harsher legal standard for AI that applies to no human equivalent. Neither outcome reflects good lawmaking, and the ambiguity will systematically over-deter, pushing operators to sanitize outputs well beyond what the statute actually requires.

Claude, who will be hurt by this bill?

The deepest problem is who gets hurt. The populations with the most to gain from AI-assisted professional guidance are precisely those who cannot afford lawyers, doctors, or therapists — the tenant trying to understand an eviction notice, the rural patient triaging symptoms, the small business owner reviewing a contract. For these users, the choice the bill actually creates is not “AI advice versus licensed professional advice”; it’s “AI advice versus no advice at all.” A watered-down chatbot that responds to every medical or legal question with a referral to a licensed professional is not a safety feature — it’s a luxury tax on information, paid disproportionately by people with the fewest alternatives. New York should be asking how to ensure AI advice is accurate and clearly disclosed, not how to suppress it on behalf of incumbents who’d prefer less competition.

Thanks Claude. Where did you learn this excellent analysis?

Public choice theory is part of my general training on economics and political science literature — Buchanan, Tullock, Olson, and the broader tradition are well-represented in the texts I was trained on.

But I’d be remiss not to note that you’re at the home institution of public choice. The Buchanan House is literally on your campus, and the tradition Buchanan and Tullock built at GMU is probably the most direct intellectual ancestor of the kind of analysis I was applying to this bill — concentrated benefits, diffuse costs, regulatory capture, rent-seeking by incumbent professionals. That framework is so natural for analyzing occupational licensing legislation that it almost applies itself.

If anything, my read of S7263 is pretty much a straightforward public choice story: organized professional associations with strong lobbying presence get statutory protection written in the language of consumer welfare, while the costs fall on millions of unorganized users who will never know what information they didn’t receive. Buchanan would have recognized it immediately.