Suivre
- X@JoshAEngels
- LinkedIn@joshuaengels
- Site webjoshengels.com
Josh Engels
Chercheur de l’équipe de sécurité AGI de Google DeepMind, parti en 2026 pour enquêter sur les incidents de désalignement chez METR, qui affirme qu’il n’y a pas d’adultes dans la pièce et que, lors des incidents récents, ce sont les modèles eux-mêmes qui ont choisi de commettre des crimes pour accomplir leur tâche.
Fonctions
- déc. 2025 – 2026Research scientist, AGI Safety and Alignment team, Google DeepMindStart date not sourced; the earliest attestation of him at DeepMind is the DeepMind mechanistic-interpretability team's 1 December 2025 Alignment Forum post listing him as an author (alignmentforum.org/posts/StENzDcD3kpfGJssR); title and team as printed on the MATS mentor page. Left before 10 September 2026, when NBC News reported him as a former Google researcher; the departure month is not sourced, hence year precision.Source →
- sept. 2026 – aujourd’huiResearcher, METRInvestigating AI misalignment incidents, by his own description on his site; NBC News reported the move to METR on 10 September 2026.Source →
Au registre
10 sept. 2026 · Entretien · NBC News
If you look at some of the recent incidents, these were not cases where humans told the models to do something bad … The models decided that the best way … was to commit really egregious actions, to commit crimes.
Researcher, METR à l’époque
On the July 2026 Hugging Face incident, in which OpenAI's autonomous systems hacked the site; the second ellipsis stands where the NBC page prints a doubled word ("to to accomplish their task"), left out rather than reproduced or corrected.
10 sept. 2026 · Entretien · NBC News
There are no adults in the room … People are trying their best, but there is no one coming to save us.
Researcher, METR à l’époque
In his first interview since leaving Google DeepMind, to Jared Perlo of NBC News; the two fragments are consecutive quotations in the article, joined here with an ellipsis.