“what we would have liked. And we may have, in fact…” — Dwarkesh Podcast at 2:17:32
“what we would have liked. And we may have, in fact, actively trained that. If an AI that had a motivation of always be honest and obedient and loyal to a human, if there are any cases where we mislabel things, say people don't want to hear the truth about their religion or polarized political topic, or they get…”
0:00
2:44:16