Hacker News new | ask | show | jobs
by r2_pilot 757 days ago
I did do some followup research. The math in its complex reasoning "tracks" but when I asked it to do 4 digit x 4 digit multiplication, it got most of it right except for a weird random digit error in the middle (?!) of the correct answer, lol. Now I want to run CLUTTR against Claude since it seems nobody has published that yet.