[looobay]

There was research on LLMs training and distillation that if two models have a similar architecture (probably the case for Xai) the "master" model will distill knowledge to the model even if its not in the distillation data. So they probably need to train a new model from scratch.

(sorry i don't remember the name but there was an example with a model liking howl to showcase this)

[-_-]

Subliminal learning: https://alignment.anthropic.com/2025/subliminal-learning/

[labrador]

If true, bad news for Elon Musk and xAI because they have to start over. He's already indicated this in regards to Wikipedia. He wants to train on Grokepedia and not Wikipedia. Removing NSFW material gives him another reason.