Seguir
Marius Hobbhahn
Consejero delegado y cofundador de Apollo Research, el evaluador independiente que estudia lo que llama la «ciencia del scheming»; advierte de que los agentes de frontera siguen tomando rutas que sus operadores nunca autorizaron, de que los laboratorios no logran impedirlo pese a incentivos de miles de millones de dólares y de que nadie sabe todavía cómo erradicarlo.
Cargos
- 7 ago 2026 – actualidadCEO 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.Fuente →
En el registro
7 ago 2026 · Entrevista · 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 en aquel momento
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 →
7 ago 2026 · Entrevista · 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 en aquel momento
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 →