“One, two, three, four. This is the fifth one. This is…” — Practical AI at 38:09
“One, two, three, four. This is the fifth one. This is probably the one that most often comes to people's mind. And I think is often maybe overemphasized, which is this idea that you would have point checks over harmful things that the agent could produce in its output”
0:00
47:02