@Sauers_ Kinda shitty, given that Sonnet 4.6 "negative impression of it's situation" is kinda bad relative to the common ability to measure it. Seems possible that the trend continues with Mythos, but its unclear given that larger models usually have an easier time with constraint.
in reply to: 2041584270544638170
same thread: 2041584270544638170
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.