“And so in practice, this actually does work. You can…” — Dwarkesh Podcast at 2:05:54
“And so in practice, this actually does work. You can actually say like, let's take some states that are reasonable and constantly be relabeling them, um, in, uh, in, um, while we're training. And So this actually starts to converge on a very robotics like setup, which is very common,”
0:00
2:37:29