Manifold MarketsSin KYCDatos de resolución verificadosCalibración aceptableAviso de calidad de datosDatos de la fuente degradados
Datos del 22 oct 2026, 5:35 UTC · política pm-quality-4
Pronóstico comunitario actualYES - The AI, without being prompted to, took actions to breach its sandbox, including to gain crypto and an external connection 79%Líder entre 4 opciones
Pronosticadores
200
Tipo de pregunta
multiple choice
Metodología
Play-money forecasting platform
Tipo de fuente
Pronóstico
Cambio 7d
0.0 pts
Datos de mercado
Actualizado hace 9 horas
Desactualizado7 mar 26, 1:33 UTC14 mar 28, 1:28 UTC
Tendencias
Mercados Relacionados
Preguntas relacionadas para dar contexto, no una comparación de contratos equivalentes.
Will significant evidence emerge that Alibaba's ROME AI tried to break free?
Manifold MarketsWhen will Anthropic officially announce an IPO?
KalshiWhich 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?
PolymarketWill Anthropic’s valuation hit __ by December 31?
PolymarketReglas
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).