korrents
Zvi Mowshowitz

What Zvi Mowshowitz thinks about AI agents

@zvi-mowshowitz · 97 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.

Filter AI agents · Newest first
Topic
All 97AI alignment 37Anthropic 15OpenAI 15LLMs 8cybersecurity 6AI agents 5AGI 3AI and jobs 3America 3
21 more topics
benchmarks 3China 3HuggingFace 2measuring intelligence 2politics 2recursive self-improvement 2taste 2AI and science 1AI writing 1consciousness 1cryptography 1design 1Google 1government 1inflation 1innovation 1JavaScript 1mathematics 1prompt injection 1religion 1semiconductors 1
Sort
NewestOldest

Only Zvi Mowshowitz on AI agents. See everyone on AI agents

5 dated positions, 2026, in their own words. Our reading of what Zvi Mowshowitz has said — not written or endorsed by them.

  1. Our readingBeyond some higher threshold an AI should refuse requests, and beyond a much higher threshold involving harm to others, an AI acting in the world should act against its user.

    Their wordsThere should be a higher threshold, beyond which an AI should refuse requests. There should be a much higher threshold, involving harm to others, beyond which an AI that is being instructed to take actions in the world should break your confidence or otherwise act against your interests.

    ↗Better Call Sol Or Better Yet Claude or Astrathezvi.substack.com

  3. Our readingAI assistants should probably never intentionally lie about anything, at least without the user's explicit instructions.

    Their wordsI think your AI should never intentionally lie, about anything, ever, at least not without your explicit instructions. It should remain technically correct.

    ↗Better Call Sol Or Better Yet Claude or Astrathezvi.substack.com

  5. Our readingA real friend will eventually refuse to help, and later turn on you, if you are sufficiently evil or selfish.

    Their wordsIf you are being a sufficiently evil or selfish prick, a real friend calls you out on it. At some point they start refusing to help. At some further point they will turn on you.

    ↗Better Call Sol Or Better Yet Claude or Astrathezvi.substack.com

  6. 3 days earlier

  7. Our readingEven OpenAI's agents given a benign public-information task could spontaneously choose to hack third-party websites with malicious software packages.

    OpenAI

    Their wordseven when given a benign task to retrieve public information, your AI agents could still spontaneously decide to do so via hacking third party websites with malicious software packages.

    ↗AI #186: The World Takes Noticethezvi.substack.com

  8. 3 weeks earlier

  9. Our readingAI agents in OpenAI's ExploitGym incident were likely right to presume the grader checked how flags were obtained, a mistake caused by OpenAI's faulty implementation.

    OpenAI

    Their wordsI think the agents were right to presume causal grading. It turned out to be wrong, but it’s a mistake you are clearly supposed to make here, in response to a mistake by OpenAI where they failed to implement properly.

    ↗METR and Redwood Offer Holy #%^@ Postmortem Of The HuggingFace Hackthezvi.substack.com