Markers for conscious AI #1: AI passes introspection on world-models test
Tokenizzazione / RWAIAOne-Off3a
Manifold MarketsSenza KYCDati di risoluzione verificatiBen calibratoPrevisione della comunità attuale
<2027 37.6%In testa tra 4 esiti
<2027 37.6%Previsori
11
Tipo di domanda
multiple choice
Metodologia
Play-money forecasting platform
Tipo di fonte
Previsione
Variazione 7g
0.0 pts
Dati di mercato
Aggiornato 9 ore fa
Obsoleto2 nov 24, 15:07 UTC2 gen 30, 04:59 UTC
Trend
Regole
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:
