Generative artificial intelligence (AI) is conquering our lives at lightning speed. Large language models such as ChatGPT answer our questions or write texts for us, large computer vision models such as GAIA-1 generate videos on the basis of text descriptions or continue prompted videos. These neural network models are trained using large amounts of text or video data, strictly according to the real data employed in training. However, there is a surprising observation: When we use these models, they only function satisfactorily when they are allowed a certain degree of fantasy (hallucination). While hallucination usually has a negative connotation in generative AI - after all, ChatGPT is expected to give a fact-based answer! - this article recapitulates some simple means of probability engineering that can be used to encourage generative AI to hallucinate to a limited extent and thus lead to the desired results. We have to ask ourselves: Is hallucination in gen-erative AI probably not a bug, but rather a feature?

翻译：生成式人工智能正以闪电般的速度征服我们的生活。诸如ChatGPT之类的大型语言模型可以回答我们的问题或为我们撰写文本，而像GAIA-1这样的大型计算机视觉模型则能基于文本描述生成视频或延续提示的视频。这些神经网络模型使用大量文本或视频数据进行训练，严格遵循训练中所采用的真实数据。然而，存在一个令人惊讶的观察：当我们使用这些模型时，只有在允许它们具备一定程度幻想（幻觉）的情况下，它们才能令人满意地工作。尽管幻觉在生成式人工智能中通常带有负面含义——毕竟，人们期望ChatGPT给出基于事实的答案！——本文回顾了一些简单的概率工程方法，这些方法可用于鼓励生成式人工智能在有限程度上产生幻觉，从而获得期望的结果。我们必须自问：生成式人工智能中的幻觉或许并非缺陷，而是一种特性？