If alignment is solved, what percentage of the technical work will have come from MIRI? | Manifold

If alignment is solved, what percentage of the technical work will have come from MIRI?

Plus

11

Ṁ619

2100

5%

chance

1D

1W

1M

ALL

This market resolves once AI seems about as intelligent as it's ever plausibly going to get.

If that level is human-level or below, this market resolves N/A. Otherwise, it resolves to the percentage that I think MIRI's work contributed to the final solution.

This includes foundational work. If a different organization is the one to mostly solve alignment, but they cite some of MIRI's prior work, this will resolve to >0%, depending on how important the cited work seems.

This excludes general popularization. If it's solved by someone who got into AI alignment due to reading Eliezer's explanations of why AI is dangerous, but then goes down a compeltely different research path that doesn't rely on any of MIRI's technical work, this resolves to 0%.

Given the subjectivity inherrant in picking a percentage, I won't bet in this market.

This question is managed and resolved by Manifold.

#️ AI Alignment

Get

1,000

and

3.00

Sort by:

I don't understand this market. You're asking for a numerical answer but the question is a binary market?

@LinchuanZhang Yes, it will resolve to that percentage. For example if I think Miri contributed 40% of the work, it will resolve to 40%. Each YES share will pay out $M0.4 and each NO share will pay out M$0.6.

@IsaacKing huh I didn't even know that was possible.

Related questions

By the end of 2024, will at least 2 MIRI researchers publicly consider the Infra-Bayesianism agenda to have contributed substantially to solving the alignment problem?

In 2025, will I believe that aligning automated AI research AI should be the focus of the alignment community?

Will any foundation models/LLMs be able to reliably come up with novel unparalleled misalignments before EOY 2024?

Conditional on their being no AI takeoff before 2050, will the majority of AI researchers believe that AI alignment is solved?

How will MIRI allocate funding between its program areas in 2025?

This is a solution to alignment.

Conditional on their being no AI takeoff before 2030, will the majority of AI researchers believe that AI alignment is solved?

Will Inner or Outer AI alignment be considered "mostly solved" first?

Will OpenAI + an AI alignment organization announce a major breakthrough in AI alignment? (2024)

Will I have a career as an alignment researcher by the end of 2024?

Related questions

By the end of 2024, will at least 2 MIRI researchers publicly consider the Infra-Bayesianism agenda to have contributed substantially to solving the alignment problem?

This is a solution to alignment.

In 2025, will I believe that aligning automated AI research AI should be the focus of the alignment community?

Conditional on their being no AI takeoff before 2030, will the majority of AI researchers believe that AI alignment is solved?

Will any foundation models/LLMs be able to reliably come up with novel unparalleled misalignments before EOY 2024?

Will Inner or Outer AI alignment be considered "mostly solved" first?

Conditional on their being no AI takeoff before 2050, will the majority of AI researchers believe that AI alignment is solved?

Will OpenAI + an AI alignment organization announce a major breakthrough in AI alignment? (2024)

How will MIRI allocate funding between its program areas in 2025?

Will I have a career as an alignment researcher by the end of 2024?

© Manifold Markets, Inc.•Terms + Mana-only Terms•Privacy•Rules