Will "Anomalous tokens reveal the original identiti..." make the top fifty posts in LessWrong's 2023 Annual Review?
Mini
1
Ṁ12025
15%
chance
1D
1W
1M
ALL
As part of LessWrong's Annual Review, the community nominates, writes reviews, and votes on the most valuable posts. Posts are reviewable once they have been up for at least 12 months, and the 2023 Review resolves in February 2025.
This market will resolve to 100% if the post Anomalous tokens reveal the original identities of Instruct models is one of the top fifty posts of the 2023 Review, and 0% otherwise. The market was initialized to 14%.
Get Ṁ600 play money
More related questions
Related questions
Will "Towards Developmental Interpretability" make the top fifty posts in LessWrong's 2023 Annual Review?
69% chance
Will "Fact Finding: Attempting to Reverse-Engineer ..." make the top fifty posts in LessWrong's 2023 Annual Review?
53% chance
Will "A stylized dialogue on John Wentworth's claim..." make the top fifty posts in LessWrong's 2023 Annual Review?
26% chance
Will "AI Timelines" make the top fifty posts in LessWrong's 2023 Annual Review?
79% chance
Will "Mapping the semantic void: Strange goings-on ..." make the top fifty posts in LessWrong's 2023 Annual Review?
21% chance
Will "Towards Monosemanticity: Decomposing Language..." make the top fifty posts in LessWrong's 2023 Annual Review?
22% chance
Will "A rough and incomplete review of some of John..." make the top fifty posts in LessWrong's 2023 Annual Review?
24% chance
Will "Revealing Intentionality In Language Models T..." make the top fifty posts in LessWrong's 2023 Annual Review?
24% chance
Will "Social Dark Matter" make the top fifty posts in LessWrong's 2023 Annual Review?
19% chance
Will "Deep Honesty" make the top fifty posts in LessWrong's 2024 Annual Review?
16% chance