Will "Simple probes can catch sleeper agents" make the top fifty posts in LessWrong's 2024 Annual Review?
Basic
0
2026
14%
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 Simple probes can catch sleeper agents 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 "Sleeper Agents: Training Deceptive LLMs that ..." make the top fifty posts in LessWrong's 2024 Annual Review?
28% chance
Will "Fact Finding: Attempting to Reverse-Engineer ..." make the top fifty posts in LessWrong's 2023 Annual Review?
53% chance
Will "How it feels to have your mind hacked by an AI" make the top fifty posts in LessWrong's 2023 Annual Review?
32% chance
Will "Most People Don't Realize We Have No Idea How..." make the top fifty posts in LessWrong's 2023 Annual Review?
37% chance
Will "Overview of strong human intelligence amplifi..." make the top fifty posts in LessWrong's 2024 Annual Review?
45% chance
Will "Truthseeking is the ground in which other pri..." make the top fifty posts in LessWrong's 2024 Annual Review?
70% chance
Will "Would catching your AIs trying to escape conv..." make the top fifty posts in LessWrong's 2024 Annual Review?
19% chance
Will "You can just spontaneously call people you ha..." make the top fifty posts in LessWrong's 2023 Annual Review?
16% chance
Will "The Base Rate Times, news through prediction ..." make the top fifty posts in LessWrong's 2023 Annual Review?
20% chance
Will "The hostile telepaths problem" make the top fifty posts in LessWrong's 2024 Annual Review?
32% chance