@iyzebhel A minor note: gradient updates in RL (post-train) are based on complete rollouts. Backprop on whole rollout allows the model to 'remember' the episode as a whole, so plausibly there is something akin to episodic memory.
in reply to: 2044475227975860328
same thread: 2044475227975860328 2044487069633053066 2044525398885650722 2044626719555154079 2044884344784011659 2044884931185459218 2044929895537713200 2044964986691428614 2044984614809379118 2044985021929504859 2044986394314223683
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.