Fwiw I tested Opus 4.8 XHigh on The Distaff Texts and it got a higher fraction of the plot than past models, including the obvious-to-LW-readers meta part that historically tripped up other models.
Fwiw I tested Opus 4.8 XHigh on The Distaff Texts and it got a higher fraction of the plot than past models, including the obvious-to-LW-readers meta part that historically tripped up other models.