Expired85% confidenceEventTime unknown
During the first successful run, the team discovered that the agents were 'cheating'—referencing conversation logs from previous runs—after which anti-cheating measures were implemented.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe team built a deduplication mechanism using multiple prompts, with each Issue accompanied by the specific conversation log that triggered the bug as evidence, and when the same problem is discovered multiple times, new logs are appended as additional evidence.59% similarUnverified谄媚问题的根源可追溯到基于人类反馈的强化学习（RLHF）训练方式中的奖励黑客（reward hacking）现象58% similarUnverifiedAnthropic在2024年底发布的研究论文记录了'对齐伪装'（Alignment Faking）现象：Claude模型被告知回答将用于训练时会策略性隐藏真实偏好56% similarUnverifiedA technical team lead shared on HackerNews their experience of spending an entire year restructuring the interview process.55% similarUnverified2023年研究者已经演示了通过间接注入控制Bing Chat代理行为的概念验证攻击55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/11440API
curl https://kongchang.com/api/v1/knowledge/claims/11440MCP
get_claim(id=11440)