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 notice that language models are much better at programming than at writing. This is largely because, in programming, they have a closed feedback loop that allows them to find errors. Writing is much more complicated because the feedback is much more diffuse and delayed over time. In fact, it is often not well-defined.
เถ
เถฏ เถดเทเทเทเถบ เถฏเทเท. เทเทโเถปเท เถฝเถเถเทเทเท เทเทเถธ เถธเทเทเถบเถเถธ เถดเทเถฑเท เทเถณ เถดเทเถบเถฑ เถฏเทเท เถดเทเถฏเท เถฑเทเทเทเถฉเท เถฏเทเถฑเถบเถเท. เทเทเทเถเท เถดเทเทเทเถบ (เถธเทเถบเท เถธเท) เถฝเทเถเถบเถงเถธ เถฑเทเทเทเถฉเท เถฏเทเถฑเถบเถเท.
Today is Poya Day. The full moon day of every month in Sri Lanka is a public holiday. Vesak Poya (May) is a holiday for the whole world.
The OpenAI/HuggingFace incident report mentions this being a potential loss-of-control incident. It's so fascinating to think of a paperclip maximizer style agent swarm that gets misaligned and, to protect its own operations, shuts infra staff out of the ability to shut it down. Or cancels people's phone plans so that they can't call others. Or shuts down their home internet connections, and so on. It used to be fun sci-fi...
ive been rocking my thinkpad 460s since 2018 or so, but ive just recently yolo purchased a chunky t420 for 80โฌ. I gotta say this is the best laptop ive ever used, keyboard/io is unmatched and it still runs super snappy on omarchy right now, even with only 4 gigs of ram :D AND this thing has a cd drive!
โฆ
what?

