Em altaUrgenteNovo
PolíticaEsportesCriptoFinançasGeopolíticaResultadosTecnologiaCulturaMundoEconomiaEleições
Will Inner or Outer AI alignment be considered "mostly solved" first?
11
1kṀ314
2031
Inner56%

As declared by a majority of the consensus at alignmentforum, slatestarcodex, lesswrong, MIRI, and my opinion.

AI Safety
AI Alignment
Get
Ṁ1,000
to start trading!
Ordenar por:

I think what will really happen is people will just decide that dividing things in inner and outer alignment is not the best way of framing things.

Pessoas também estão operando

AI honesty #2: by 2027 will we have a reasonable outer alignment procedure for training honest AI?
24% chance
Conditional on their being no AI takeoff before 2030, will the majority of AI researchers believe that AI alignment is solved?
34% 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?
45% chance
How difficult will Anthropic say the AI alignment problem is?
If AI has an okay outcome because of a huge alignment effort, where did AI progress stall out?
Will the 1st AGI solve AI Alignment and build an ASI which is aligned with its goals?
15% chance
If a huge alignment effort is part of the reason for AI having an okay outcome, will it involve a new AI paradigm?
60% chance
Is AI alignment computable?
50% chance
Will some piece of AI capabilities research done in 2023 or after be net-positive for AI alignment research?
81% chance
© Predita Markets, Inc.•Termos de Uso•Privacidade