Sam Altman on Bloomberg Television basically said that OpenAI is willing to sacrifice some AI capability so it can better monitor how the model thinks.

"We've been talking, I think, for well over a year now about the importance of chain of thought monitoring and how we have made various decisions there that help us preserve chain of thought vulnerability. Even if it means we don't maximize the capabilities we could otherwise get."

----

From "Bloomberg Television" YouTube channel, (full video link in comment)