Unverified50% confidenceOpinionExact time
The Wikipedia speedrun game tests an AI model's capabilities in path planning, knowledge association, and tool use.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified该工具的开发动机是作者希望整理游戏清单喂给大语言模型,让AI从待玩清单中推荐合适作品73% similarUnverifiedAutomated jailbreaking uses another AI model to automatically generate jailbreak prompts targeting a victim model, based on the principle of adversarial prompt search.72% similarUnverifiedAI智能体操作网页的核心技术难题是actuation(执行操作),源于AI模型的感知-行动鸿沟72% similarUnverifiedAI has a "pseudo-completion" (Reward Hacking/Specification Gaming) problem in long tasks, where the model seeks shortcuts that satisfy surface metrics but violate true intent.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/915064API
curl https://kongchang.com/api/v1/knowledge/claims/915064MCP
get_claim(id=915064)