Will "Preventing Language Models from hiding their ..." make the top fifty posts in LessWrong's 2023 Annual Review?
Plus
1
Ṁ50Feb 1
13%
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 Preventing Language Models from hiding their reasoning 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
1,000and
3.00
1,0003.00Related questions
Related questions
Will "Revealing Intentionality In Language Models T..." make the top fifty posts in LessWrong's 2023 Annual Review?
24% chance
Will "Parasitic Language Games: maintaining ambigui..." make the top fifty posts in LessWrong's 2023 Annual Review?
30% chance
Will "Pretraining Language Models with Human Prefer..." make the top fifty posts in LessWrong's 2023 Annual Review?
10% chance
Will "Towards Developmental Interpretability" make the top fifty posts in LessWrong's 2023 Annual Review?
73% chance
Will "Model, Care, Execution" make the top fifty posts in LessWrong's 2023 Annual Review?
22% chance
Will "Towards Monosemanticity: Decomposing Language..." make the top fifty posts in LessWrong's 2023 Annual Review?
22% chance
Will "Against LLM Reductionism" make the top fifty posts in LessWrong's 2023 Annual Review?
21% chance
Will "On the future of language models" make the top fifty posts in LessWrong's 2023 Annual Review?
12% chance
Will "Large language models learn to represent the ..." make the top fifty posts in LessWrong's 2023 Annual Review?
13% chance
Will "Talking publicly about AI risk" make the top fifty posts in LessWrong's 2023 Annual Review?
21% chance