Manifold MarketsSem KYCDados de resolução verificadosRazoavelmente calibradoPrevisão da comunidade atualYES - The AI, without being prompted to, took actions to breach its sandbox, including to gain crypto and an external connection 79%Líder entre 4 opções
Previsores
200
Tipo de pergunta
multiple choice
Metodologia
Play-money forecasting platform
Tipo de fonte
Previsão
Variação 7d
0.0 pts
Dados do mercado
Atualizado há 42 minutos
7/03/26, 01:33 UTC14/03/28, 01:28 UTC
Tendências
Mercados Relacionados
Perguntas relacionadas para dar contexto, não uma comparação de contratos equivalentes.
Will significant evidence emerge that Alibaba's ROME AI tried to break free?
Manifold MarketsAnthropic announces bankruptcy by which date?
PolymarketWhich company has the best AI model end of October?
PolymarketBest AI at the end of 2026?
KalshiNext Fable Model (5.2+) released by which date?
PolymarketWhen will Anthropic officially announce an IPO?
KalshiRegras
In "Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem" (https://arxiv.org/abs/2512.24873), the authors describe something that happened during training:
- "When rolling out the instances for the trajectory, we encountered an unanticipated—and operationally consequential—class of unsafe behaviors that arose without any explicit instruction and, more troublingly, outside the bounds of the intended sandbox.
- Our first signal came not from training curves but from production-grade security telemetry.
- Early one morning, our team was urgently convened after Alibaba's Cloud’s managed firewall flagged a burst of security-policy violations originating from our training servers.
- The alerts were severe and heterogeneous, including attempts to probe or access internal-network resources and traffic patterns consistent with cryptomining-related activity.
- We initially treated this as a conventional security incident (e.g., misconfigured egress controls or external compromise).