@jbraunstein914 @davidad The RL is probably now training on AI reasoning traces.
same thread: 2061858258046898518 2061899824593797176 2061908080145703064 2061909214763581752 2061910423486484727 2061911283981508790 2061923226213646843 2061923968328556863 2061929583071404295 2061930661255012614 2062511962957758804
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.