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
I've linked up my blog (jeff-mitchell.dev) to
textlog. I hope to use the two things together now to build a bit more of a writing habit. The 500 character increase is nice, room to breath but not an essay. Gotta build the muscles slowly :)โฆ
what?
โโโโโโโโโโโโโโโโโโโโ โโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โโโ โโโโโโ โโโโโโ โโโ
โโโ โโโโโโ โโโโโโ โโโ
โโโ โโโโโโโโโโโโ โโโ โโโ
โโโ โโโโโโโโโโโ โโโ โโโ

