Will "Sleeper Agents: Training Deceptive LLMs that ..." make the top fifty posts in LessWrong's 2024 Annual Review?
Basic
2
Ṁ372026
28%
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 2024 Review resolves in February 2026.
This market will resolve to 100% if the post Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training is one of the top fifty posts of the 2024 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 "Discussion: Challenges with Unsupervised LLM ..." make the top fifty posts in LessWrong's 2023 Annual Review?
3% chance
Will "Lessons On How To Get Things Right On The Fir..." make the top fifty posts in LessWrong's 2023 Annual Review?
55% chance
Will "Alignment Implications of LLM Successes: a De..." make the top fifty posts in LessWrong's 2023 Annual Review?
37% chance
Will "Paper: LLMs trained on “A is B” fail to learn..." make the top fifty posts in LessWrong's 2023 Annual Review?
10% chance
Will "Against LLM Reductionism" make the top fifty posts in LessWrong's 2023 Annual Review?
21% chance
Will "Model, Care, Execution" make the top fifty posts in LessWrong's 2023 Annual Review?
22% chance
Will "Agentized LLMs will change the alignment land..." make the top fifty posts in LessWrong's 2023 Annual Review?
10% chance
Will "My Clients, The Liars" make the top fifty posts in LessWrong's 2024 Annual Review?
14% chance
Will "“Reframing Superintelligence” + LLMs + 4 years" make the top fifty posts in LessWrong's 2023 Annual Review?
13% chance
Will "AI doom from an LLM-plateau-ist perspective" make the top fifty posts in LessWrong's 2023 Annual Review?
11% chance