Manifold MarketsSin KYCDatos de resolución verificadosBien calibradoPronóstico comunitario actualNo 56.9%
Pronosticadores
8
Tipo de pregunta
binary
Metodología
Play-money forecasting platform
Tipo de fuente
Pronóstico
Datos de mercado
Actualizado hace 2 horas
Desactualizado4 dic 25, 12:35 UTC31 dic 26, 23:59 UTC
Tendencias
Reglas
Some of the apparent generalisation of LLMs is actually hidden interpolation on semantic duplicates of the test set that get included in training corpuses.
- These are really hard to filter out.
- e.g. See that at least 7 of the 30 AIME 2025 questions were present on the internet before the competition.
- Resolution: at the end of next year, will I believe that >25% of apparent (i.e. ECI) AI progress 2023-2026 is actually hidden interpolation?
- My current fraction (Dec 2025): 35%
- If you want to use a model of me as well as your model of AI to answer, here are some of my views.
