We've been building Kyoto, an AI for your taxes.
It scores 100% on TaxCalcBench v2: all 50 test cases correct across federal and state returns, on every scored line. The best frontier model scores 64%.
this is one of those reasons why I don't think most people will really generate their own software
good software is a set of strong opinions and I'd rather have something that's been really thought through by someone else
Check out Code Mode, a new, experimental way for Claude Code to work with tools. Claude writes scripts that chain your tools together in sophisticated ways, and it can answer you while long commands are still running.
Opt in with CLAUDE_CODE_EXPERIMENTAL_CODE_MODE=1 https://t.co/Aj5ofLiK1y
@michaelrbock Haha I think OpenAI took their time with setting up their RL properly this time to make the model a little skeptical because of the hacks it did earlier and its attempts to cheat.