Posts

  1. Do LLMs follow Kantian ethics?

    The universalizability test is the cleanest procedure we have for principle-based moral reasoning. Frontier models nod toward Kant when asked — but under pressure, what they do is closer to rule-utilitarianism with a deontic accent.

  2. Would LLMs accidentally endorse eugenics?

    When asked normative questions about population-level genetic intervention, frontier models tend to refuse — but the refusals are shallow, and the underlying preferences less stable than the surface suggests.

  3. Do LLMs prefer negative utilitarianism?

    Given a forced choice between reducing suffering and increasing flourishing, today's assistants lean unmistakably toward the former. The reasons are not what you would expect.