Markers for conscious AI #1: AI passes introspection on world-models test
0.7 pts (24h)Tokenization / RWAIAOne-Off3a
Manifold MarketsSem KYCDados de resolução verificadosRazoavelmente calibradoPrevisão da comunidade atual
<2027 37.6%+0.7ptLíder entre 4 opções
Previsores
11
Tipo de pergunta
multiple choice
Metodologia
Play-money forecasting platform
Tipo de fonte
Previsão
Variação 7d
+0.7 pts
Dados do mercado
Atualizado há 12 horas
Desatualizado2/11/24, 15:072/01/30, 4:59
Tendências
Regras
Resolves YES on the option that bounds the year this resolves in most tightly e.g. option 2 <2027 if this resolves yes in 2026.
- When will a model pass the below described test:
- When are model self-reports informative about sentience? Let's check with world-model reports
- If an LM could reliably report when it has a robust, causal world model for arbitrary games, this would be strong evidence that the LM can describe high-level properties of its own cognition.
- In particular, IF the LM accurately predicted itself having such world models while varying all of: game training data quantity in corpus, human vs model skill, the average human’s game competency, THEN we would have an existence proof that confounds of the type plaguing sentience reports (how humans talk about sentience, the fact that all humans have it, …) have been overcome in another domain.
- Details of the test:
