Is AI alignment computable?
6
71
Ṁ154Ṁ150
2089
33%
chance
1D
1W
1M
ALL
Get Ṁ200 play money
Sort by:
@cockathiel what do you mean by “computable”? Is this just in principle? (If so I think most things should be computable in principle or at least have very good computable approximations, because “computable” is an extremely broad and flexible category.)
Related questions
Related questions
Will OpenAI + an AI alignment organization announce a major breakthrough in AI alignment? (2024)
33% chance
Will OpenAI release a technical report on a model designed for AI alignment research? (2024)
64% chance
Conditional on their being no AI takeoff before 2030, will the majority of AI researchers believe that AI alignment is solved?
37% chance
In 2025, will I believe that aligning automated AI research AI should be the focus of the alignment community?
48% chance
By 2028, will I believe that contemporary AIs are aligned (posing no existential risk)?
35% chance
Will the next Millennium Problem be solved by an AI?
45% chance
Conditional on their being no AI takeoff before 2050, will the majority of AI researchers believe that AI alignment is solved?
51% chance
Will I focus on the AI alignment problem for the rest of my life?
62% chance
Conditional on AI alignment being solved, will governments or other entities be capable of enforcing use of aligned AIs?
37% chance
Will OpenAI announce a major breakthrough in AI alignment in 2024?
42% chance