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
An interesting thought: historically, a major consideration for companies choosing what to use is how many engineers use it (because that will make hiring much easier/harder). Going forward, this becomes "how big of a corpus of this code is out there", because it impacts how proficient are likely to be at using it.
โฆ
what?
I never have enough time but Iโd love to do a bit more recreational programming with esoterical languages like kitten, , and . AoC and Project Euler are good because they just require an answer but thereโs also loads of simple puzzles online that rely on being able to submit the code in common languages. Iโve been wondering, however, if I could use an LLM to take those problems and create a verification harness for any language I like.

