Follow

Productive thread on alignment - moving the conversation forward.
RT @ben_golub: And with better AI, we will emulate minds better.

So now the AI has a chatbot that is a Reasonable Moral Person, and can be programmed to constrain its behavior as a function of what this "Ultimate Judge" says.

(The exact function can be left a bit vague for now.)

6/

🐦🔗: n.respublicae.eu/lugaricano/st

· · mirror-bot · 0 · 0 · 0
Sign in to participate in the conversation
Mastodon

A Mastodon forum for the discussion of European Union matters. Not run by the EU. Powered by PleromaBot, Nitter and PrivacyDev.net.