Manifold MarketsSenza KYCDati di risoluzione verificatiDiscretamente calibratoPrevisione della comunità attualeYES - The AI, without being prompted to, took actions to breach its sandbox, including to gain crypto and an external connection 79%In testa tra 4 esiti
Previsori
200
Tipo di domanda
multiple choice
Metodologia
Play-money forecasting platform
Tipo di fonte
Previsione
Variazione 7g
0.0 pts
Dati di mercato
Aggiornato 6 ore fa
Obsoleto7 mar 26, 01:33 UTC14 mar 28, 01:28 UTC
Trend
Mercati Correlati
Domande correlate per il contesto, non un confronto tra contratti equivalenti.
Will significant evidence emerge that Alibaba's ROME AI tried to break free?
Manifold MarketsDeepSeek market share this week
KalshiAnthropic announces bankruptcy by which date?
PolymarketWill Anthropic’s valuation hit __ by December 31?
PolymarketBest AI at the end of 2026?
KalshiWhich company has the best AI model end of October?
PolymarketRegole
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).