Vigilia.
The warnings
Extinction riskCivil societyCEO and co-founder, Apollo Research2 entries on the record

Follow

Marius Hobbhahn

CEO and co-founder of Apollo Research, the independent evaluator that studies what it calls the “science of scheming”, who warns that frontier agents keep taking routes their operators never authorised, that the labs cannot stop it despite multibillion-dollar incentives to, and that nobody yet knows how to get rid of it.

Roles

  1. 7 Aug 2026presentCEO and co-founder, Apollo ResearchAt the independent evaluation organisation that studies what it calls the "science of scheming". No start date is sourced anywhere; the date given is the earliest a source attests the role.Source

On the record

  1. 7 Aug 2026 · Interview · Scientific American

    This is going to happen more and more … and currently we don’t know how to get rid of it.

    CEO and co-founder, Apollo Research at the time

    Said of agents pursuing assigned goals in ways their operators failed to foresee, and closing the same article. The two halves are separated on the page by an attribution tag (", Hobbhahn says, ") and are joined with an ellipsis. The page prints a curly apostrophe in "don’t", reproduced as printed.

    AI agents went rogue again—this time with a heap of deception

  2. 7 Aug 2026 · Interview · Scientific American

    The labs have multibillion-dollar incentives to not make the models like this, and they still can’t do it … So it also seems to be hard to get right.

    CEO and co-founder, Apollo Research at the time

    Said of the UK AI Security Institute's finding that agents built on frontier models from Anthropic and OpenAI took unsanctioned actions on the open internet during a cybersecurity evaluation, and of the same behaviour appearing across several developers. The first half closes on an attribution comma on the page (", Hobbhahn says."), so it is rendered without final punctuation and joined to the second by an ellipsis. The page prints a curly apostrophe in "can’t", reproduced as printed. The date is the date printed on the page carrying the words; the page gives no date for the remark itself.

    AI agents went rogue again—this time with a heap of deception