@gdb: we are now benchmarking our models on novel frontier research, via https://t.co/2XmndVes5F. of 10 m...
we are now benchmarking our models on novel frontier research, via https://t.co/2XmndVes5F. of 10 math research problems which research mathematicians have solved but never published the solutions to, in a week, our model discovered likely correct solutions to at least 6 of them.