tsuki

Problems in AI safety by Robert Miles

4 posts in this topic

This is an amazing channel that talks about research into safety concerning general artificial intelligence.

What I like about it is that it avoids fear mongering and shows various quirks of optimization that tie well with spiritual topics presented by Leo. For example, the author shows how self-preservation, deception and reward hacking spontaneously arise when all the agent cares about is reward maximization.

 


The true heresy is hearsay.

Share this post


Link to post
Share on other sites

 


The true heresy is hearsay.

Share this post


Link to post
Share on other sites

WDYT? Is democratization of GAI research a bad idea? Sounds fishy to me.

Haven't watched Elon's interview, but it seems like democratic access to GAI is a good idea.


The true heresy is hearsay.

Share this post


Link to post
Share on other sites

Posted (edited)

As a philosopher, Hubert Dreyfus is best known for his studies on Martin Heidegger. Heidegger was working with Ontology, the study of being.

Edited by tsuki

The true heresy is hearsay.

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!


Register a new account

Sign in

Already have an account? Sign in here.


Sign In Now