[Redwood Research] Will we submit the bash control project to NeurIPS?
11
90
αΉ617αΉ210
May 18
9%
chance
1D
1W
1M
ALL
We're working on a follow-up to AI Control: Improving Safety Despite Intentional Subversion, in a language model agent shell programming setting. We intend to write this up and submit it to NeurIPS. Will we succeed?
Currently, we have a preliminary dataset, and we've done some back-and-forth on trusted monitoring.
The main reason we wouldn't submit is that we don't think our results are sufficiently solid by then. We won't submit if we think it's very unlikely (<20%) the paper will be accepted.
(Feel free to message me if you want to beta read the paper.)
Get αΉ200 play money
More related questions
Related questions
Will my ICML submission be accepted?
80% chance
By when will Redwood Research "finish" publishing our sandbagging project?
Will @firstuserhere coauthor a NeurIPS or ICML conference publication before end of 2024? (10,000 Mana subsidy)
28% chance
Will we have an AI generated research paper accepted to > 1 top ML conference by 2028?
71% chance
Will any of the "Will [*] coauthor a NeurIPS or ICML conference publication before end of 2024?" markets resolve to YES?
72% chance
Will we have an AI generated research paper accepted to > 1 top ML conference by 2026?
46% chance
Will a project from the Interpretability Hackathon 3.0 be accepted to a major conference?
60% chance
Will we have an AI generated research paper accepted to > 1 top ML conference by 2025?
18% chance
Will I submit a first author (or cofirst author) conference paper to ICLR, NeurIPS or ICML in 2024?
71% chance
Will we have an AI generated research paper accepted to > 1 top ML conference by 2027?
62% chance