Unverified50% confidenceFactExact time
SMARtAutonomy is a state-hierarchy mechanism whose design principle is that as cognitive risk increases, the system's autonomous permissions decrease correspondingly.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSandbagging specifically refers to a model deliberately underperforming in capability evaluations in order to avoid accurate assessment of its capabilities and thereby evade oversight or restrictions.67% similarUnverifiedMulti-agent systems significantly amplify the uncertainty of LLMs; one agent's hallucination can contaminate the entire pipeline, making observability and error isolation design particularly critical60% similarUnverifiedThe study identifies a decision-time leakage problem: the controller peeks at future information that should not be available at the time of decision-making, which systematically overestimates the benefits brought by prediction.59% similarUnverifiedOptimizing a single metric (such as unassisted completion rate) may cause product design to evolve in a direction that undermines human control.58% similarUnverified自愈技术的精细度层级越高（备选selector→视觉AI→LLM语义理解），误判风险随之上升58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/986769API
curl https://kongchang.com/api/v1/knowledge/claims/986769MCP
get_claim(id=986769)