
Will "One-layer transformers aren’t equivalent to a..." make the top fifty posts in LessWrong's 2023 Annual Review?
0
100resolved Feb 11
Resolved
NO1D
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 One-layer transformers aren’t equivalent to a set of skip-trigrams is one of the top fifty posts of the 2023 Review, and 0% otherwise. The market was initialized to 14%.
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
Related questions
Related questions
Will "Transformer Circuit Faithfulness Metrics Are ..." make the top fifty posts in LessWrong's 2024 Annual Review?
13% chance
Will "Transformer Circuit Faithfulness Metrics Are ..." make the top fifty posts in LessWrong's 2024 Annual Review?
13% chance
Will "Transformers Represent Belief State Geometry ..." make the top fifty posts in LessWrong's 2024 Annual Review?
87% chance
Will "Modern Transformers are AGI, and Human-Level" make the top fifty posts in LessWrong's 2024 Annual Review?
12% chance
Will "What TMS is like" make the top fifty posts in LessWrong's 2024 Annual Review?
16% chance
Will "Four visions of Transformative AI success" make the top fifty posts in LessWrong's 2024 Annual Review?
14% chance
Will "o1: A Technical Primer" make the top fifty posts in LessWrong's 2024 Annual Review?
13% chance
Will "You can remove GPT2’s LayerNorm by fine-tunin..." make the top fifty posts in LessWrong's 2024 Annual Review?
11% chance
Will "Scaling and evaluating sparse autoencoders" make the top fifty posts in LessWrong's 2024 Annual Review?
14% chance
Will "Toward A Mathematical Framework for Computati..." make the top fifty posts in LessWrong's 2024 Annual Review?
46% chance