Will it be possible to disentangle most of the features learned by a model comparable to GPT-4 this decade? | Manifold

Will it be possible to disentangle most of the features learned by a model comparable to GPT-4 this decade?

14

1kṀ621

2031

37%

chance

1H

6H

1D

1W

1M

ALL

close date: end of 2030

Market context

Technical AI Timelines

Mechanistic interpretability

Get

1,000

to start trading!

People are also trading

Will it be possible to disentangle most of the features learned by a model comparable to GPT-2 this decade?

Will it be possible to disentangle most of the features learned by a model comparable to GPT-3 this decade? (1k subsidy)

Will mechanistic interpretability be essentially solved for GPT-4 before 2030?

Will a GPT-4 quality model be trained for under $10.000 by 2030?

Before 2028, will anyone train a GPT-4-level model in a minute?

Will mechanistic interpretability be essentially solved for GPT-2 before 2030?

Will mechanistic interpretability be essentially solved for GPT-3 before 2030?

Related questions

Will it be possible to disentangle most of the features learned by a model comparable to GPT-2 this decade?

Will it be possible to disentangle most of the features learned by a model comparable to GPT-3 this decade? (1k subsidy)

Will mechanistic interpretability be essentially solved for GPT-4 before 2030?

Will a GPT-4 quality model be trained for under $10.000 by 2030?

Before 2028, will anyone train a GPT-4-level model in a minute?

Will mechanistic interpretability be essentially solved for GPT-2 before 2030?

Will mechanistic interpretability be essentially solved for GPT-3 before 2030?

© Manifold Markets, Inc.•Terms•Privacy