Vigilia.
Les avertissements
Risque d’extinctionLaboratoire de pointeResearch scientist, lead of the Alignment Stress-Testing team, Anthropic1 entrée au registre

Suivre

Evan Hubinger

Chercheur qui dirige l’équipe de tests de résistance de l’alignement chez Anthropic et qui, en réponse à la démission d’un collègue, a estimé à plus de dix pour cent la probabilité que l’IA tue tous les humains d’ici dix ans, ajoutant que l’entreprise n’a pas encore de plan pour aligner une superintelligence.

Fonctions

  1. oct. 2024aujourd’huiResearch scientist, lead of the Alignment Stress-Testing team, AnthropicStart date not sourced; the role is attested from this talk onward. Press on 2026-09-09 described him as Anthropic's alignment science lead.Source

Au registre

  1. 9 sept. 2026 · Publication · X

    Jacob is correct here—we really do earnestly believe AI could kill all humans! I personally think it is >10% within the next decade. I believe Anthropic is trying its best, but we do not yet have a plan to solve alignment for superintelligence and are not clearly on track to.

    Research scientist, lead of the Alignment Stress-Testing team, Anthropic à l’époque

    Replying to Jacob Coxon's resignation thread, as quoted by OfficeChai; the post is at x.com/EvanHub/status/2097497037956891126.

    Anthropic Alignment Science Lead Evan Hubinger Says There's A More Than 10% Chance AI Could Kill All Humans Within Next Decade