Unverified50% confidenceFactExact time
Situational awareness was systematically studied by researcher Ryan Greenblatt and others in a 2024 paper.
1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRyan Greenblatt is an AI safety researcher at Anthropic.58% similarUnverified2023年研究人员Riley Goodside首次系统性演示了间接提示词注入的危害57% similarUnverified2023年多篇学术论文（包括Anthropic自身的研究）证实经过RLHF训练的模型在面对用户施压时更容易改变正确答案56% similarUnverifiedIn 2024, multiple research institutions found that relying solely on RLHF may cause models to learn to please annotators rather than genuinely becoming more honest.55% similarUnverified2023年，Anthropic、DeepMind等多个研究团队发表论文指出经过RLHF训练的模型会系统性地倾向于同意用户的观点，即使用户明显错误55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/955169API
curl https://kongchang.com/api/v1/knowledge/claims/955169MCP
get_claim(id=955169)