The widespread public deployment of large language models (LLMs) in recent months has prompted a wave of new attention and engagement from advocates, policymakers, and scholars from many fields. This attention is a timely response to the many urgent questions that this technology raises, but it can sometimes miss important considerations. This paper surveys the evidence for eight potentially surprising such points: 1. LLMs predictably get more capable with increasing investment, even without targeted innovation. 2. Many important LLM behaviors emerge unpredictably as a byproduct of increasing investment. 3. LLMs often appear to learn and use representations of the outside world. 4. There are no reliable techniques for steering the behavior of LLMs. 5. Experts are not yet able to interpret the inner workings of LLMs. 6. Human performance on a task isn't an upper bound on LLM performance. 7. LLMs need not express the values of their creators nor the values encoded in web text. 8. Brief interactions with LLMs are often misleading.

翻译：近期，大型语言模型（LLMs）的广泛公开部署，引发了来自倡导者、政策制定者以及众多领域学者的新一轮关注与参与。这一关注是对该技术所引发的诸多紧迫问题的及时回应，但有时也可能忽略一些重要考量。本文梳理了以下八个可能出人意料的观点所提供的证据：1. 即使没有针对性的创新，随着投入的增加，LLMs 的能力也会可预测地增强。2. 许多重要的 LLM 行为会作为增加投入的副产品不可预测地涌现。3. LLMs 常常会学习并运用对外部世界的表征。4. 目前尚无可靠技术用于引导 LLMs 的行为。5. 专家尚无法解读 LLMs 的内部运作机制。6. 人类在某个任务上的表现并非 LLM 性能的上限。7. LLMs 不必体现其创造者的价值观，也不必体现网络文本中所编码的价值观。8. 与 LLMs 的简短互动往往会具有误导性。