[ value alignment ] research often frames the problem as: first, learn the human 'value function' --- for every possible state of the world…
Suppose I have an agent that generates text. I want it to generate text that is [ value alignment|aligned ] with human values. Approaches…
Implement MuZero or something similar. What are the 'state of the art' RL algorithms? What is known and not known about [ value alignment ]?
In no particular order. Items may move to [ previously read ] if I read them or former reading inbox if I decide I'm not currently…
[ writing inbox ] the privilege of having correct advice work out for you ([ the privilege of advice working out ]) Let's stipulate that any…
How do you start building and selling [ computational therapy ]? It can't just be a medical product, because that's a hugely regulated and…
See also: [ computational life coach ] A recurring dream I have is to use AI to solve mental health. It is simultaneously one of the most…
An idea I got from [ John Higgs ]'s discussion of metamodernism is that taking [ all models are wrong ] to its logical conclusion requires…