logoalt Hacker News

StevenWaterman • today at 3:32 PM • 1 reply • view on HN

You don't need RL all the way to ASI. You just need RL far enough that the model becomes good enough at AI research that it discovers something better than RL.


Replies

codewithcheese • today at 3:37 PM

> becomes good enough at AI research that it discovers something better than RL

That might require continuous learning without verifiable rewards. RL models might help humans join the dots faster, but we don't know how many years that will take.

If its not possible with neural nets as we know them now, and requires a number of completely novel breakthroughs, there could be far from exponential progress even with the best RL models.

➕ show 1 reply