RT by @karpathy: 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 text. Vintage models should help us to understand how LMs generalize (e.g., can we teach talkie to code?). Thread:· 与古人对话：13B模型仅用1931年前文本训练

<p>New work with <a href="https://rss.xcancel.com/AlecRad" title="Alec Radford">@AlecRad</a> and <a href="https://rss.xcancel.com/DavidDuvenaud" title="David Duvenaud">@DavidDuvenaud</a>:<br> <br> Have you ever dreamed of talking to someone from the past? Introducing talkie, a 13B model trained only on pre-1931 text. <br> <br> Vintage models should help us to understand how LMs generalize (e.g., c