AI alignment
3 statements across 2 episodes · 1 bullish · 0 bearish · 2 people on the record · first statement Oct 16, 2025 by Jerry Tworek · across every show →
Everything said about AI alignment, oldest first
Oct 16, 2025
Tworek: AI alignment is a never-ending pursuit as human goals evolve
“And it's I think it's a never ending pursuit because like, even, even for humans, it's not super easy to define what's, what do we consider a light? And I think as our civilization will evolve, it will, the notion of alignment and the goals of humanity will, K…”
Oct 23, 2025
Schrittwieser: AI safety must span the entire stack, not just RL
“Yeah, I wouldn't view it alignment adjust like an RL problem. I think it sort of, it goes throughout the whole stack. You might, you know, for example, filter the pre-training data in some way. You might, after training, you might have classifiers that, you kn…”
Oct 23, 2025 positive
Pre-training aids AI alignment by implicitly instilling human values
“I definitely think we would keep using pre-training data, not just from an efficiency point of view as well, but also I think there is interesting safety angles, because by pre-training and, you know, all this human knowledge, we're implicitly creating an agen…”