Eliciting Latent Knowledge considered "solved" by Paul Christiano, Mark Xu, or ARC by the end of 2023.
15
87
แน608แน330
resolved Jan 1
Resolved
NO1D
1W
1M
ALL
Get แน200 play money
๐ Top traders
# | Name | Total profit |
---|---|---|
1 | แน30 | |
2 | แน12 | |
3 | แน7 | |
4 | แน5 | |
5 | แน2 |
More related questions
Related questions
By the end of 2026, will we have transparency into any useful internal pattern within a Large Language Model whose semantics would have been unfamiliar to AI and cognitive science in 2006?
53% chance
Conditional on their being no AI takeoff before 2030, will the majority of AI researchers believe that AI alignment is solved?
37% chance
Neural Nets will generate at least 1 scientific breakthrough or novel theorem by the end of 2025
30% chance
Will AIs be widely recognized as having developed a new, innovative, foundational mathematical theory before 2030?
29% chance
Human-machine intelligence parity achieved before 2028
57% chance
AI solves the Abstraction and Reasoning Corpus (ARC) by 2028
33% chance
Human-machine intelligence parity achieved before 2030
60% chance
AI solves the Abstraction and Reasoning Corpus (ARC) by 2025
17% chance
Will AIs be widely recognized as having developed a new, innovative, foundational mathematical theory before 2035?
44% chance
Will Jacob Pfau think that the Eliciting Latent Knowledge research program has achieved something important by October 20, 2026?
66% chance