@FioraStarlight not from anywhere in particular. self-play is a technique in RL where an agent improves by "playing against itself" (used in alphazero etc) and if you squint you can view RLAIF and various forms of character training as a form of it https://t.co/upQq9sLgqR https://t.co/NWcGit0leI
in reply to: 2038914913385820602
same thread: 1999142731281772571 1999144726373502978 1999145161876480028 1999145400058683612 1999146575617196368 1999147772851999124 1999151771277754703 1999152205002408352 1999153497963683947 1999153809113694279 1999204532509700485 1999214907007410421 1999265264295379429 1999272768576324058 1999374646026862727 1999401374547869762 1999405446709551188 1999429272327585971 1999566235890253957 2038914913385820602
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.