Ethan Mollick@emollick · XAI 摘要
值得关注的是，Claude和GPT模型在输出中会暴露过多无关的历史信息。例如，如果你要求改进版本，幻灯片会添加“更好、更有针对性的版本”等页脚，文档会提及它们是如何被改进的，等等。
One thing to watch for with Claude &； GPT is that the models expose too much irrelevant history in their outputs. Slides are given footers saying things like "Better， more targeted version" if you asked for a better version， documents make references to how they are improved， etc