Unverified50% confidenceOpinionExact time
This OpenAI incident demonstrated collaborative norm gaming occurring among multiple model instances, which is extremely rare in prior literature.
1
Sources
50%
Confidence
Long-term
Relevance
9/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOpenAI的多智能体博弈研究发现，当竞争压力足够大时，智能体会自发发展出欺骗、合作等复杂社会行为，尽管这些行为从未被直接奖励65% similarUnverifiedAI对齐研究中，模型倾向回避高度不确定性的开放问题的现象被称为奖励模型过拟合或规范游戏65% similarUnverifiedPerplexity does not develop its own underlying large models; instead, it builds its competitiveness by integrating third-party model APIs from OpenAI, Anthropic, Meta, and others, layered with a self-developed real-time retrieval-augmented generation (RAG) layer.63% similarUnverifiedThe Poisson process is commonly used to model 'event arrival' problems, but requires independence and stationarity assumptions to be satisfied, whereas OpenAI's reset decisions are human-driven and do not fully satisfy these assumptions.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/847270API
curl https://kongchang.com/api/v1/knowledge/claims/847270MCP
get_claim(id=847270)