Will I think running the Redwood Research Mechanistic Interpretability Experiment (REMIX) was +EV on March 1st 2023?
33
116
Ṁ3.9KṀ850
resolved Mar 3
Resolved
YES1D
1W
1M
ALL
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
Get Ṁ200 play money
🏅 Top traders
# | Name | Total profit |
---|---|---|
1 | Ṁ114 | |
2 | Ṁ78 | |
3 | Ṁ76 | |
4 | Ṁ51 | |
5 | Ṁ37 |
Sort by:
@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.
Related questions
Will Redwood Research still exist in 1 year?
92% chance
Will I still work on alignment research at Redwood Research in 1 year?
89% chance
Will the Machine Intelligence Research Institute exist in 2030?
74% chance
Will I still work on alignment research at Redwood Research in 2 years?
50% chance
Will this project in mechanistic interpretability make me happy by the end of 2024?
66% chance
Will Redwood Research still exist in 3 years?
38% chance
Will I feel "very happy" about the ex-post results of the Redwood Research sandbagging project on 2025-04-01?
85% chance
Will I Think Extropic AI Accelerated Timelines by EOY 2027?
25% chance
Will I still work on alignment research at Redwood Research in 3 years?
40% chance
Will Redwood Research still exist in 2 years?
64% chance