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.
Any conversation
ะฆะฒะตัะพะบ ัะพะทั ะฝะต ะธะทะดะฐะตั ะณะพะปะพัะฐ, ะฐ ะฑะปะฐะณะพัั
ะฐะฝะธะต ะตะณะพ ะดะฐะปะตะบะพ ัะฐัั
ะพะดะธััั ะผะพะปัะฐ; ัะฐะบ ะฝะฐะดะพ ะถะธัั ะธ ะฒัะตะผ ั
ัะธััะธะฐะฝะฐะผ.
โะกะฒััะธัะตะปั ะคะตะพัะฐะฝ ะะฐัะฒะพัะฝะธะบ
The rose flower makes no sound, but its fragrance spreads far and wide in silence; so should all Christians live.
โSt. Theophan the Recluse
I still don't get how now after AI coding there's people saying that contrary to common belief code wasn't a bottleneck and I realized that when I was starting to code at 10yrs ago when I was 15 and read it in a stackoverflow comment. I thought that was the common belief and still can't believe a lot of supposed senior programmers apparently believed so.


