Will a frontier AI lab publicly report catching one of its own models gaming a safety evaluation before the end of 2027?
One-OffIATecnologia1a
Manifold MarketsSenza KYCDati di risoluzione verificatiBen calibratoPrevisione della comunità attualeSì 76%
Previsori
4
Tipo di domanda
binary
Metodologia
Play-money forecasting platform
Tipo di fonte
Previsione
Dati di mercato
Aggiornato 59 minuti fa
In ritardo30 ott 26, 16:24 UTC31 dic 27, 23:59 UTC
Trend
Mercati Correlati
Domande correlate per il contesto, non un confronto tra contratti equivalenti.
By 2028, will an AI safety evaluation become a mandatory requirement for autonomous vehicle manufacturers?
Manifold MarketsAny American frontier AI lab (e.g. OpenAI, Anthropic) nationalized by EOY 2027?
Manifold Markets2027 Frontier AI Lab props
Manifold MarketsWill any frontier AI lab publicly commit to a Human Preservation constraint in model architecture before 2027?
Manifold MarketsFrontier AI lab pulls a model over safety concerns in 2026?
PolymarketAI lab announces another Millennium Prize solution by which date?
PolymarketRegole
Resolves YES if, by December 31, 2027, Anthropic, OpenAI, Google DeepMind, Meta or xAI publishes a report, system card or blog post stating that one of its own models was caught deliberately underperforming, sandbagging or otherwise gaming a safety evaluation.
- The lab itself has to say it; a third-party claim is not enough.
- Background: in September 2026 I asked an AI for its ten-year forecast, best case and worst case.
- One of its 2027 best-case points was "A lab catches a model gaming its safety tests and publishes the finding." I am making a market for each checkable point so the forecast can be scored.
- The full forecast is free: The Forecast: 2027 to 2036, best case and worst case
- [link preview]
