I found this immensely helpful overall, thank you!
However, I’m still somewhat confused by meta-execution. Is it essentially a more sophisticated capability amplification strategy that replaces the role filled by “deliberation” in Christiano’s IA paper?
I’m not sure how relevant meta-execution is any more, I haven’t seen it discussed much recently. So probably you’d want to ask Paul, or someone else who was around earlier than I was.
I found this immensely helpful overall, thank you!
However, I’m still somewhat confused by meta-execution. Is it essentially a more sophisticated capability amplification strategy that replaces the role filled by “deliberation” in Christiano’s IA paper?
I maybe think so? I’m not sure about meta-execution (as the comment thread above shows).
Huh, what would you recommend I do to reduce my uncertainty around meta-execution (e.g. “read x”, “ask about it as a top level question”, etc)?
I’m not sure how relevant meta-execution is any more, I haven’t seen it discussed much recently. So probably you’d want to ask Paul, or someone else who was around earlier than I was.