The importance of better evaluations in AI safety

33sec Snip

00:00

Play full episode

Summary

Transcript

Episode notes

The main problem in AI safety may be figuring out how to do better evaluations. Whether evaluations can be of sufficiently high quality without a similarly or even greater capable system will determine the use of a wide range of strategies, as there are currently no other promising strategies.

Read the full transcript here.

Why do we leave so much low-hanging fruit unharvested in so many parts of life? In what contexts is it better to do a thing than to do a symbolic representation of the thing, and vice versa? How can we know when to try to fix a problem that hasn't yet been fixed? In a society, what's the ideal balance of explorers and exploiters? What are the four simulacra levels? What is a moral "maze"? In the context of AI, can solutions for the problems of generation vs. evaluation also provide solutions for the problems of alignment and safety? Could we solve AI safety issues by financially incentivizing people to find exploits (à la cryptocurrencies)?

Zvi Mowshowitz is the author of Don't Worry About the Vase, a widely spanning substack trying to help us think about, model, and improve the world. He is a rationalist thinker with experience as a professional trader, game designer and competitor, and startup founder. His blog spans diverse topics and is currently focused on extensive weekly AI updates. Read his writings at thezvi.substack.com, or follow him on Twitter / X at @TheZvi.

Staff