This is an incredibly cool experiment It is also fascinating that the model knows information up to 1931, but, at least in some science topi…

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 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:

Related

• Anyhow, very impressive achievement, and a very solid model. Based on vibes, the gap seems around the same as it has always been between clo…
• Seems like a good model from Meta that is still trailing the current series of releases. The most important thing to note is that it is not …
• There are more competitive small model makers, but there is still a very big gap between what small models can do and what large models can …
• It isn't at the level of the Big Three models when you poke at it, but a very solid start.
• Anyhow, its not bad. Just not the vibe level that the benchmarks might indicate. And, for a first re-entry into the frontier model space, gi…

Source: Ethan Mollick (X) | 2026-04-28