logoalt Hacker News

origini • today at 5:57 PM • 1 reply • view on HN

With RL it will learn from all misstakes once while with humans after a generation, information might just be gone.

Its a possible as an attack vector for sure.

But in comparision to nature, compute can speedrun all of this with RL.


Replies

disgruntledphd2 • today at 6:28 PM

RL data is really really really expensive to collect and train on, and only works for verifiable tasks, which is not most tasks.

Even a lot of what software professionals do isn't verifiable.