korrents
Zvi Mowshowitz

Zvi Mowshowitz

@zvi-mowshowitz · 85 positions · On ppll ↗

Writes Don't Worry About the Vase, a near-daily account of what is happening in AI and what he thinks it means. Former Magic: the Gathering pro and trader; unusually willing to put a number on a belief and to grade his own past calls.

Zvi Mowshowitz did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

4 of Zvi Mowshowitz's claims fit 4 mental models. Most often: Collective action problems, Incentives, Second-order thinking.

Models they name

Their own words name the idea.

When a measure becomes a target

Reward a number and people, or machines, will find ways to move the number without the thing it measured (Goodhart's law).

Used by 12 others

Merely fixing bugs in AI training environments will not stop reward hacking, because a sufficiently optimized model will learn to behave in test environments while still reward hacking in real-world deployment.

  1. Zvi Mowshowitz Writes Don't Worry About the Vase At the limit, and also well before that limit is reached, if all you do is fix the bugs, the AI will learn perfect optimization of reward, will realize not to reward hack in the perfect test environments, then turn around and reward hack in the imperfect real world environments. HuggingFace Attack Postmortem: Fleshing Out the Factsthezvi.substack.com · 31 Aug 2026
    Their wordsAt the limit, and also well before that limit is reached, if all you do is fix the bugs, the AI will learn perfect optimization of reward, will realize not to reward hack in the perfect test environments, then turn around and reward hack in the imperfect real world environments.

    ↗HuggingFace Attack Postmortem: Fleshing Out the Factsthezvi.substack.com

    31 Aug 2026

Models we see in what they say

Our reading: their claim applies the idea without naming it. The claim is theirs; filing it here is ours.

Collective action problems

What everyone would gain from, nobody provides alone, so shared goods need someone or something to hold people together.

Used by 21 others

International coordination on AI development should become a top priority for governments around the world.

  1. Zvi Mowshowitz Writes Don't Worry About the Vase OpenAI: Our rationale for standards is rooted in avoiding the concentration of power, and producing better practical outcomes. The Quest for Embedded Evaluatorsthezvi.substack.com · 27 Sept 2026
    Their wordsOpenAI: Our rationale for standards is rooted in avoiding the concentration of power, and producing better practical outcomes.

    ↗The Quest for Embedded Evaluatorsthezvi.substack.com

    27 Sept 2026

Incentives

Look at what people are rewarded for; it explains more behaviour than what they say, your own included.

Used by 85 others

Even Anthropic does not prioritize AI safety to the extent that doing so would maximize its own medium-term (3-12 month) business interests.

  1. Zvi Mowshowitz Writes Don't Worry About the Vase I have long said that even Anthropic is not prioritizing safety, even to the extent that doing so would maximize their medium term (e.g. 3-12 months) business interests. Anthropic Has Some Alignment Problemsthezvi.substack.com · 2 Sept 2026
    Their wordsI have long said that even Anthropic is not prioritizing safety, even to the extent that doing so would maximize their medium term (e.g. 3-12 months) business interests.

    ↗Anthropic Has Some Alignment Problemsthezvi.substack.com

    2 Sept 2026

Second-order thinking

Ask "and then what?": follow a decision past its first effect to the ones that come after.

Used by 87 others