Will Inner or Outer AI alignment be considered "mostly solved" first?
11
Ṁ3142031
Inner56%
1D
1W
1M
ALL
As declared by a majority of the consensus at alignmentforum, slatestarcodex, lesswrong, MIRI, and my opinion.
Get Ṁ1,000 play money
Related questions
Related questions
In 2025, will I believe that aligning automated AI research AI should be the focus of the alignment community?
53% chance
Will OpenAI + an AI alignment organization announce a major breakthrough in AI alignment? (2024)
22% chance
Is AI alignment computable?
34% chance
Conditional on AI alignment being solved, will governments or other entities be capable of enforcing use of aligned AIs?
37% chance
Conditional on their being no AI takeoff before 2030, will the majority of AI researchers believe that AI alignment is solved?
35% 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?
63% chance
Will OpenAI + an AI alignment organization announce a major breakthrough in AI alignment? (2024)
8% chance
Will xAI significantly rework their alignment plan by the start of 2026?
63% chance
AI honesty #2: by 2027 will we have a reasonable outer alignment procedure for training honest AI?
25% chance