RyanGreenblatt avatar
Ryan Greenblatt
closes Mar 1
Will I think running the Redwood Research Mechanistic Interpretability Experiment (REMIX) was +EV on March 1st 2023?

See https://www.lesswrong.com/posts/nqwzrpkPvviLHWXaE/apply-to-the-redwood-research-mechanistic-interpretability
Context: I work at Redwood.

REMIX starts on 12/19/2022.

Resolves to N/A if REMIX is canceled (very unlikely as it starts on Monday).

Edit: ex-post EV analysis

Sort by:
NoaNabeshima avatar
Noa Nabeshimais predicting NO at 64%

Is this relative to the baseline of the next best thing Redwood and Remix participants would do with the time+resources or something else?

RyanGreenblatt avatar
Ryan Greenblatt

@NoaNabeshima the criteria is "suppose we had decided not to do remix and instead used the resources elsewhere etc. Would this have been higher expected utility? (given ex-post knowledge about the quality of remix and what we otherwise would have done)." I might edit this into the description.

RyanGreenblatt avatar
Ryan Greenblatt

I plausibly should have made this market before we commited to running REMIX.