Will the OpenAI superalignment team believe that their goal has been achieved after 4 years? | Manifold

Will the OpenAI superalignment team believe that their goal has been achieved after 4 years?

Technical AI Timelines

43

358

Ṁ5.5K

Ṁ850

2027

27%

chance

1D

1W

1M

ALL

https://openai.com/blog/introducing-superalignment

Introducing Superalignment

We need scientific and technical breakthroughs to steer and control AI systems much smarter than us. To solve this problem within four years, we’re starting a new team, co-led by Ilya Sutskever and Jan Leike, and dedicating 20% of the compute we’ve secured to date to this effort. We’re looking for e…

Get Ṁ200 play money

Sort by:

I'll just say that if our only criteria for whether we have reached alignment is "the team believes they succeeded", we have absolutely no hope of actually reaching it.

Related in Technical AI Timelines

Will GPT5 show clear signs of diminishing returns?

-7% 1d64% chance

Will a large language model beat a super grandmaster playing chess by 2028?

See more Technical AI Timelines questions

More related questions

Will OpenAI achieve "very high level of confidence" in their "Superalignment" solutions by 2027-07-06?

Will OpenAI publicly state that they DON'T know how to safely align a superintelligence, after 2027?

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

Will OpenAI remain independent by EOY 2024?

Will we solve AI alignment by 2026?

Will Ilya Sutskever still lead OpenAI’s Superalignment team at the end of 2024? [ACX 2024]

Will OpenAI still be doing Superalignment in June 2024?

Will general consensus be that OpenAI is no longer the lead AI company by end of 2024?

Will OpenAI announce a major breakthrough in AI alignment in 2024?

By 2028, will I think OpenAI has been net-good for the world?

Technical AI Timelines questions

Will GPT5 show clear signs of diminishing returns?

Will a large language model beat a super grandmaster playing chess by 2028?

Related questions

Will OpenAI achieve "very high level of confidence" in their "Superalignment" solutions by 2027-07-06?

Will Ilya Sutskever still lead OpenAI’s Superalignment team at the end of 2024? [ACX 2024]

Will OpenAI publicly state that they DON'T know how to safely align a superintelligence, after 2027?

Will OpenAI still be doing Superalignment in June 2024?

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

Will general consensus be that OpenAI is no longer the lead AI company by end of 2024?

Will OpenAI remain independent by EOY 2024?

Will OpenAI announce a major breakthrough in AI alignment in 2024?

Will we solve AI alignment by 2026?

By 2028, will I think OpenAI has been net-good for the world?