Ethan Mollick@emollick · XAI 摘要
LLM 幻觉虽无法避免，但人类早已发展出应对之策。通过建立组织结构来处理不可靠信息并降低错误风险，这种数百年验证有效的方法同样适用于 AI。
Hallucinations remain in LLMs， but note that over centuries we have developed complicated， successful machines that take uncertain output from unreliable sources &； reduce the risk of errors.
We call those machines organizational structures &； we can apply similar approaches to AI