For those looking for the answer that don’t want to click through the entire repo: no. Kimi cannot do your American taxes, but origin doesn’t seem to matter.
It appears that no LLM can get more than about a third of returns correct. Kimi K3 is on par with Sonnet 5. They are both very bad at doing your taxes.
2 comments of 6
[ 0.94 ms ] story [ 9.9 ms ] threadIt appears that no LLM can get more than about a third of returns correct. Kimi K3 is on par with Sonnet 5. They are both very bad at doing your taxes.
In 6 months an LLM will get it to 80%
people will exclaim negatively “it was trained on the eval [to do this incredibly useful thing]”
meanwhile a problem is solved