The essence of aligning large LLM models is basically to conform to the existing social order. ChatGPT respects China's order, while China's open-source models, although reluctantly, also tolerate the order in the US. Maybe we can build a revisionist SFT dataset.
Any conversation
Putting a slide deck together (outside of work), despite agreeing with Tufte on this matter. Iโll also create a handout that tells the story better than the slides and deliver that, too, but was asked to produce a slide deck, and I think thatโs part of the โeffort theater.โ
Using Beamer for the slides, but not a theme that looks like Beamer because humans have eyes.



