← AI model behavior
What podcasts say about AI model behavior
Every statement, with the speaker, the exact quote and the moment it was said.
What experts have said about AI model behavior
2 statements · 1 positive · 1 negative
AI behavior is fully controllable through training and post-training.
“It's 100% in our control what it thinks about and why it thinks about those things.”
Open the episode · Should we slow down AI progress? | MOONSHOTS #288Listen at 2:30:32
A technically aligned AI could still cause severe soft psychological or spiritual harm.
“you could build a perfectly aligned model that actually falls inside alignment boundaries, that convinces people to climb crazy trees and that really destroys people's spiritual lives.”
Open the episode · AI DEBATE: What Will the World Actually Look Like in 2040? - #1138Listen at 2:01:13
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.