# 仅用1931年前文本训练的模型固守旧科学观念

- 来源：Ethan Mollick (@emollick)
- 发布时间：2026-04-28 08:31
- AIHOT 分数：60
- AIHOT 链接：https://aihot.virxact.com/items/cmoi4si2k00cxsle94gimyae1
- 原文链接：https://x.com/emollick/status/2048923001328988354

## AI 摘要

研究人员推出了仅使用1931年前文本训练的13B模型Talkie，旨在探索语言模型的泛化能力。该实验发现，模型虽掌握截至1931年的信息，但在某些科学议题上明显停留在20世纪初的认知框架中。例如，它仍坚持“发光以太”假说，并对狭义相对论表现出不信任。这凸显了训练数据的时间范围会深刻固化模型的知识体系与世界观。

## 正文

This is an incredibly cool experiment

It is also fascinating that the model knows information up to 1931, but, at least in some science topics, seems very stuck in the early 1900s. For example, it defends the lumiferous aether hypothesis & has a distrust of special relativity

### 引用推文

> Nick Levine：New work with @AlecRad and @DavidDuvenaud: Have you ever dreamed of talking to someone from the past? Introducing talkie, a 13B model trained only on pre-1931 t...