[ot][spam][crazy] thread for relevance stuff
the ideas of making rerieval and storage structures off e.g. pretrained models are quite pleasant and need much more implementation my biggest cognitive issues with relevance relates to learning and retaining it. pretrained models do retaining but learning isn’t strongly engaged. still, humans can learn pretty effectively from clear examples. it seems nice to consider relevance exploration to me. something that looks through to connect. connecting information together is so important! extreme conceptual censorship is deadly imo are two things relevant? can we associate them if they are?
another inhibited process for me is the path of behavior from goal through plan to action goal, plan, action. this is possibly similar to relevance in that plans are formed from relevant steps to meet goals, and actions are then formed from relevant substeps in the context of whether preceding ones succeeded or not. feedback from a changing world state into all parts.
connecting information together is so important! extreme conceptual censorship is deadly imo
are two things relevant? can we associate them if they are?
something you could make here is a debate generator that finds conflicting viewpoints, information that backs the viewpoints, and then synthesizes a conversation between people holding them. it could also form various further viewpoints from the various combinations of the possible reasons for them. that engages computer relevance, of course we need human discourse rather than simulated discourse. it’s healing to see but you wouldn’t want it used for social or political planning ideally.
with dissociative disorder / mind control, there are various regions of conceptual space where a mystery steps in and roughly guides things away. so for me, some things are easier to associate than others. [pretrained models have a slight similarity since they have baked skillsets]
participants (1)
-
Undescribed Horrific Abuse, One Victim & Survivor of Many