[ot][notes][ai][worldpeace] Hyperint. Draft

Karl gmkarl at gmail.com
Mon Dec 20 16:49:56 PST 2021


[spam][looking around the neighborhood at bikesheds while my scooter
drives around on its own]

daydreaming on a seed setup part

- maybe there could be large-n reinforcement learning models
- maybe they could each have a random location in m-dimensional space,
and be able to move themselves in their action space.  this produces
relative distance.
- idea of exposing model-specific weights based on distance
- idea of observation and action spaces could include neighbor
weights, so different kinds of communication evolve.  there could also
be data that is not weights.

then there's the idea of stimulating it to take off learning faster
and faster.  maybe it would make sense to advance wire models so that
they learn to teach other to learn.


More information about the cypherpunks mailing list