← Gli avvertimenti
Rischio di estinzioneLaboratorio di frontieraResearch scientist, lead of the Alignment Stress-Testing team, Anthropic1 voce a registro
Seguire
- X@EvanHub
- Sito webalignmentforum.org
Evan Hubinger
Ricercatore che guida il team di stress test dell’allineamento in Anthropic e che, rispondendo alle dimissioni di un collega, ha stimato sopra il dieci per cento la probabilità che l’IA uccida tutti gli esseri umani entro un decennio, aggiungendo che l’azienda non ha ancora un piano per allineare una superintelligenza.
Ruoli
- ott 2024 – oggiResearch 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.Fonte →
A registro
9 set 2026 · Post · 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 all’epoca
Replying to Jacob Coxon's resignation thread, as quoted by OfficeChai; the post is at x.com/EvanHub/status/2097497037956891126.