Manifold MarketsSans KYCDonnées de résolution vérifiéesAssez bien calibréPrévision communautaire actuelleYES - The AI, without being prompted to, took actions to breach its sandbox, including to gain crypto and an external connection 79%En tête parmi 4 options
Prévisionnistes
200
Type de question
multiple choice
Méthodologie
Play-money forecasting platform
Type de source
Prévision
Variation 7j
0.0 pts
Données du marché
Mis à jour il y a 2 heures
Obsolète7 mars 26, 01:33 UTC14 mars 28, 01:28 UTC
Tendances
Marchés Associés
Questions liées pour le contexte, et non une comparaison de contrats équivalents.
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?
PolymarketRègles
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).