“There could be a situation where like, by looking at the…” — Dwarkesh Podcast at 1:09:51
“There could be a situation where like, by looking at the chain of thought, we can see, oh, the model is scheming and doing this along things in a way that's actually not being detected in our line metrics. Now, the problem is that it's very tempting to then intervene based on that”
0:00
1:20:10