Unverified50% confidenceFactExact time
The adversarial collaboration study on theories of consciousness published in 2023 was funded by the Templeton Foundation and organized different theoretical teams to design pre-registered experiments to test the predictions of IIT and GWT.
1
Sources
50%
Confidence
Long-term
Relevance
8/17/2026
First Seen
Sources
计算机科学家能否造出一个大脑？两种技术路线深度解析
Related Claims
Unverified2023年以来研究人员在AutoGPT、LangChain等主流Agent框架中演示了提示注入攻击的可行性62% similarUnverified斯坦福HAI研究院2021年发布报告《On the Opportunities and Risks of Foundation Models》，由100余位研究者联合撰写60% similarUnverified该独立研究者的Phrasome Theory框架获得了期刊评审具有原创性的鼓励性反馈，但最终未获发表60% 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59% similarUnverifiedDeepMind与牛津大学、爱丁堡大学合作开发的Ithaca模型于2022年发表于《Nature》58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/762578API
curl https://kongchang.com/api/v1/knowledge/claims/762578MCP
get_claim(id=762578)