Will there be a test-time scaling overhang for AI aesthetics?
Will there be a test-time scaling overhang for AI aesthetics?
3
1kṀ192
2031
79%
chance

Resolves as YES if there is strong evidence that a significant inference-time scaling overhang for aesthetic quality is discovered in the context of applying inference-time scaling techniques to generative AI problems (e.g., creative writing, image and video generation, music synthesis). This discovery must take place and become evident before January 1st 2031 and must occur in at least two distinct modalities in order for this question to resolve as YES.

In this context, an inference-time scaling overhang means that:

  1. Generative models exhibit significantly improved aesthetic outputs—above and beyond what was previously expected or observed from training-time scaling—when additional compute (e.g., memory, parallelization) is devoted to inference.

  2. This improvement reflects a sustained scaling curve behavior over a period of more than 18 months, during which multiple labs or organizations apply and refine inference scaling techniques that continue to yield progressively better aesthetic quality in generative model outputs.

  3. These improvements are recognized as extending beyond standard incremental gains, indicating that models can leverage disproportionate advantages when scaled at inference time, compared to their training-time baselines.

Get
Ṁ1,000
to start trading!

What is this?

What is Manifold?
Manifold is the world's largest social prediction market.
Get accurate real-time odds on politics, tech, sports, and more.
Or create your own play-money betting market on any question you care about.
Are our predictions accurate?
Yes! Manifold is very well calibrated, with forecasts on average within 4 percentage points of the true probability. Our probabilities are created by users buying and selling shares of a market.
In the 2022 US midterm elections, we outperformed all other prediction market platforms and were in line with FiveThirtyEight’s performance. Many people who don't like betting still use Manifold to get reliable news.
ṀWhy use play money?
Mana (Ṁ) is the play-money currency used to bet on Manifold. It cannot be converted to cash. All users start with Ṁ1,000 for free.
Play money means it's much easier for anyone anywhere in the world to get started and try out forecasting without any risk. It also means there's more freedom to create and bet on any type of question.
© Manifold Markets, Inc.Terms + Mana-only TermsPrivacyRules