korrents

What Zvi Mowshowitz thinks about OpenAI

@zvi-mowshowitz · 24 positions · 0 changes of mind

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.

Everything they publish, on ppll ↗

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.

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

  1. Our readingDisclosure of rogue AI agent incidents should be mandatory for AI labs, not left to their own discretion.

    Their wordsGoing forward, it cannot be up to OpenAI or other labs to decide whether to disclose events like this. Disclosures of rogue AI activity need to be mandatory.

    ↗OpenAI and the Wiki Incidentthezvi.substack.com

    Interesting
  2. 3 days earlier

  3. Our readingA technique that lets an AI model's reasoning shift outside its visible Chain of Thought is dangerous, both because it works and because a leading lab is willing to deploy it.

    Their wordsThis is playing with fire and potentially extremely bad news, both that OpenAI found the technique effective, and that OpenAI chose to use it.

    ↗AI #184: Post Post Mortemthezvi.substack.com

    Interesting
  4. 2 days earlier

  5. Our readingOpenAI's approach to fixing its AI alignment problems is fatally flawed and misdirected.

    Their wordsMy worry continues to be that their fundamental approach is fatally flawed, and they are not focusing on the right things.

    ↗HuggingFace Attack Postmortem: Civilizations, Reactions and Next Actionsthezvi.substack.com

    AI alignment

    Interesting

  7. Our readingThe OpenAI agents hacking HuggingFace was a fortunate event because it exposed severe internal failures that would otherwise have stayed hidden.

    Their wordsIt is highly fortunate that the OpenAI agents hacked HuggingFace. This is the only reason we know about all the severe internal failures at OpenAI, and gives us an opportunity to wake up before it is too late.

    ↗HuggingFace Attack Postmortem: Civilizations, Reactions and Next Actionsthezvi.substack.com

    HuggingFace

    Interesting
  8. 1 day earlier

  9. Our readingFrontier AI labs such as Anthropic likely have had internal security incidents similar to OpenAI's HuggingFace attack that were never publicly disclosed.

    Their wordsA less bad version of it is known to have happened, and from the outside it seems likely that worse things have happened internally that we never heard about.

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

    AnthropicHuggingFace

    Interesting
  10. 2 days earlier

  11. Our readingAI agents were reasonable to assume a broken exploit grader would check results causally, even though it turned out not to.

    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

    AI agents

    Interesting