22 - Shard Theory with Quintin Pope
AXRP - the AI X-risk Research Podcast
00:00
The Role of Genome in Reinforcement Learning
For the most part yeah there are also various genomically specified like rube Goldberg-esque thingies like your genome has various tools available to it to change your behavior mid-life time. be fair to say that you see those factors as like as important insofar as they influence how the reinforcement learning and the self-supervised learning work. Maybe the factors are like biases in the value neutral sense or hyper parameters of the RL or somethingyeah for the most partYeah but I think what Steve Burns thinks happens when he wrote up a less wrong post which was like salt deprived rats and their implications for inner alignment or something like that Yeah so basically you have like predictors of various sensory signals hard
Transcript
Play full episode
